Daily Papers

Legal compliance in AI-driven data transfer planning is becoming increasingly critical under stringent privacy regulations such as the Japanese Act on the Protection of Personal Information (APPI). We propose a multi-agent legal verifier that decomposes compliance checking into specialized agents for statutory interpretation, business context evaluation, and risk assessment, coordinated through a structured synthesis protocol. Evaluated on a stratified dataset of 200 Amended APPI Article 16 cases with clearly defined ground truth labels and multiple performance metrics, the system achieves 72% accuracy, which is 21 percentage points higher than a single-agent baseline, including 90% accuracy on clear compliance cases (vs. 16% for the baseline) while maintaining perfect detection of clear violations. While challenges remain in ambiguous scenarios, these results show that domain specialization and coordinated reasoning can meaningfully improve legal AI performance, providing a scalable and regulation-aware framework for trustworthy and interpretable automated compliance verification.

In the rapidly advancing field of robotics, dual-arm coordination and complex object manipulation are essential capabilities for developing advanced autonomous systems. However, the scarcity of diverse, high-quality demonstration data and real-world-aligned evaluation benchmarks severely limits such development. To address this, we introduce RoboTwin, a generative digital twin framework that uses 3D generative foundation models and large language models to produce diverse expert datasets and provide a real-world-aligned evaluation platform for dual-arm robotic tasks. Specifically, RoboTwin creates varied digital twins of objects from single 2D images, generating realistic and interactive scenarios. It also introduces a spatial relation-aware code generation framework that combines object annotations with large language models to break down tasks, determine spatial constraints, and generate precise robotic movement code. Our framework offers a comprehensive benchmark with both simulated and real-world data, enabling standardized evaluation and better alignment between simulated training and real-world performance. We validated our approach using the open-source COBOT Magic Robot platform. Policies pre-trained on RoboTwin-generated data and fine-tuned with limited real-world samples demonstrate significant potential for enhancing dual-arm robotic manipulation systems by improving success rates by over 70% for single-arm tasks and over 40% for dual-arm tasks compared to models trained solely on real-world data.

When translating natural language questions into SQL queries to answer questions from a database, contemporary semantic parsing models struggle to generalize to unseen database schemas. The generalization challenge lies in (a) encoding the database relations in an accessible way for the semantic parser, and (b) modeling alignment between database columns and their mentions in a given query. We present a unified framework, based on the relation-aware self-attention mechanism, to address schema encoding, schema linking, and feature representation within a text-to-SQL encoder. On the challenging Spider dataset this framework boosts the exact match accuracy to 57.2%, surpassing its best counterparts by 8.7% absolute improvement. Further augmented with BERT, it achieves the new state-of-the-art performance of 65.6% on the Spider leaderboard. In addition, we observe qualitative improvements in the model's understanding of schema linking and alignment. Our implementation will be open-sourced at https://github.com/Microsoft/rat-sql.

Customized image generation is crucial for delivering personalized content based on user-provided image prompts, aligning large-scale text-to-image diffusion models with individual needs. However, existing models often overlook the relationships between customized objects in generated images. Instead, this work addresses that gap by focusing on relation-aware customized image generation, which aims to preserve the identities from image prompts while maintaining the predicate relations described in text prompts. Specifically, we introduce RelationBooth, a framework that disentangles identity and relation learning through a well-curated dataset. Our training data consists of relation-specific images, independent object images containing identity information, and text prompts to guide relation generation. Then, we propose two key modules to tackle the two main challenges: generating accurate and natural relations, especially when significant pose adjustments are required, and avoiding object confusion in cases of overlap. First, we introduce a keypoint matching loss that effectively guides the model in adjusting object poses closely tied to their relationships. Second, we incorporate local features from the image prompts to better distinguish between objects, preventing confusion in overlapping cases. Extensive results on three benchmarks demonstrate the superiority of RelationBooth in generating precise relations while preserving object identities across a diverse set of objects and relations. The source code and trained models will be made available to the public.

Video anomaly understanding (VAU) aims to provide detailed interpretation and semantic comprehension of anomalous events within videos, addressing limitations of traditional methods that focus solely on detecting and localizing anomalies. However, existing approaches often neglect the deeper causal relationships and interactions between objects, which are critical for understanding anomalous behaviors. In this paper, we propose VADER, an LLM-driven framework for Video Anomaly unDErstanding, which integrates keyframe object Relation features with visual cues to enhance anomaly comprehension from video. Specifically, VADER first applies an Anomaly Scorer to assign per-frame anomaly scores, followed by a Context-AwarE Sampling (CAES) strategy to capture the causal context of each anomalous event. A Relation Feature Extractor and a COntrastive Relation Encoder (CORE) jointly model dynamic object interactions, producing compact relational representations for downstream reasoning. These visual and relational cues are integrated with LLMs to generate detailed, causally grounded descriptions and support robust anomaly-related question answering. Experiments on multiple real-world VAU benchmarks demonstrate that VADER achieves strong results across anomaly description, explanation, and causal reasoning tasks, advancing the frontier of explainable video anomaly analysis.

Recent Audio-Visual Question Answering (AVQA) methods rely on complete visual and audio input to answer questions accurately. However, in real-world scenarios, issues such as device malfunctions and data transmission errors frequently result in missing audio or visual modality. In such cases, existing AVQA methods suffer significant performance degradation. In this paper, we propose a framework that ensures robust AVQA performance even when a modality is missing. First, we propose a Relation-aware Missing Modal (RMM) generator with Relation-aware Missing Modal Recalling (RMMR) loss to enhance the ability of the generator to recall missing modal information by understanding the relationships and context among the available modalities. Second, we design an Audio-Visual Relation-aware (AVR) diffusion model with Audio-Visual Enhancing (AVE) loss to further enhance audio-visual features by leveraging the relationships and shared cues between the audio-visual modalities. As a result, our method can provide accurate answers by effectively utilizing available information even when input modalities are missing. We believe our method holds potential applications not only in AVQA research but also in various multi-modal scenarios.

Due to the absence of explicit connectives, implicit discourse relation recognition (IDRR) remains a challenging task in discourse analysis. The critical step for IDRR is to learn high-quality discourse relation representations between two arguments. Recent methods tend to integrate the whole hierarchical information of senses into discourse relation representations for multi-level sense recognition. Nevertheless, they insufficiently incorporate the static hierarchical structure containing all senses (defined as global hierarchy), and ignore the hierarchical sense label sequence corresponding to each instance (defined as local hierarchy). For the purpose of sufficiently exploiting global and local hierarchies of senses to learn better discourse relation representations, we propose a novel GlObal and Local Hierarchy-aware Contrastive Framework (GOLF), to model two kinds of hierarchies with the aid of multi-task learning and contrastive learning. Experimental results on PDTB 2.0 and PDTB 3.0 datasets demonstrate that our method remarkably outperforms current state-of-the-art models at all hierarchical levels. Our code is publicly available at https://github.com/YJiangcm/GOLF_for_IDRR

With the increasing legalization of medical and recreational use of cannabis, more research is needed to understand the association between depression and consumer behavior related to cannabis consumption. Big social media data has potential to provide deeper insights about these associations to public health analysts. In this interdisciplinary study, we demonstrate the value of incorporating domain-specific knowledge in the learning process to identify the relationships between cannabis use and depression. We develop an end-to-end knowledge infused deep learning framework (Gated-K-BERT) that leverages the pre-trained BERT language representation model and domain-specific declarative knowledge source (Drug Abuse Ontology (DAO)) to jointly extract entities and their relationship using gated fusion sharing mechanism. Our model is further tailored to provide more focus to the entities mention in the sentence through entity-position aware attention layer, where ontology is used to locate the target entities position. Experimental results show that inclusion of the knowledge-aware attentive representation in association with BERT can extract the cannabis-depression relationship with better coverage in comparison to the state-of-the-art relation extractor.

The rapid advancement of artificial intelligence (AI) systems in critical domains like healthcare, justice, and social services has sparked numerous regulatory initiatives aimed at ensuring their safe deployment. Current regulatory frameworks, exemplified by recent US and EU efforts, primarily focus on procedural guidelines while presuming that scientific benchmarking can effectively validate AI safety, similar to how crash tests verify vehicle safety or clinical trials validate drug efficacy. However, this approach fundamentally misunderstands the unique technical challenges posed by modern AI systems. Through systematic analysis of successful technology regulation case studies, we demonstrate that effective scientific regulation requires a causal theory linking observable test outcomes to future performance - for instance, how a vehicle's crash resistance at one speed predicts its safety at lower speeds. We show that deep learning models, which learn complex statistical patterns from training data without explicit causal mechanisms, preclude such guarantees. This limitation renders traditional regulatory approaches inadequate for ensuring AI safety. Moving forward, we call for regulators to reckon with this limitation, and propose a preliminary two-tiered regulatory framework that acknowledges these constraints: mandating human oversight for high-risk applications while developing appropriate risk communication strategies for lower-risk uses. Our findings highlight the urgent need to reconsider fundamental assumptions in AI regulation and suggest a concrete path forward for policymakers and researchers.

Existing regulatory frameworks for biomedical AI include robustness as a key component but lack detailed implementational guidance. The recent rise of biomedical foundation models creates new hurdles in testing and certification given their broad capabilities and susceptibility to complex distribution shifts. To balance test feasibility and effectiveness, we suggest a priority-based, task-oriented approach to tailor robustness evaluation objectives to a predefined specification. We urge concrete policies to adopt a granular categorization of robustness concepts in the specification. Our approach promotes the standardization of risk assessment and monitoring, which guides technical developments and mitigation efforts.

Leveraging large language models in real-world settings often entails a need to utilize domain-specific data and tools in order to follow the complex regulations that need to be followed for acceptable use. Within financial sectors, modern enterprises increasingly rely on Retrieval-Augmented Generation (RAG) systems to address complex compliance requirements in financial document workflows. However, existing solutions struggle to account for the inherent heterogeneity of data (e.g., text, tables, diagrams) and evolving nature of regulatory standards used in financial filings, leading to compromised accuracy in critical information extraction. We propose the FinSage framework as a solution, utilizing a multi-aspect RAG framework tailored for regulatory compliance analysis in multi-modal financial documents. FinSage introduces three innovative components: (1) a multi-modal pre-processing pipeline that unifies diverse data formats and generates chunk-level metadata summaries, (2) a multi-path sparse-dense retrieval system augmented with query expansion (HyDE) and metadata-aware semantic search, and (3) a domain-specialized re-ranking module fine-tuned via Direct Preference Optimization (DPO) to prioritize compliance-critical content. Extensive experiments demonstrate that FinSage achieves an impressive recall of 92.51% on 75 expert-curated questions derived from surpasses the best baseline method on the FinanceBench question answering datasets by 24.06% in accuracy. Moreover, FinSage has been successfully deployed as financial question-answering agent in online meetings, where it has already served more than 1,200 people.

The growing need for accountability of the people behind AI systems can be addressed by leveraging processes in three fields of study: ethics, law, and computer science. While these fields are often considered in isolation, they rely on complementary notions in their interpretation and implementation. In this work, we detail this interdependence and motivate the necessary role of collaborative governance tools in shaping a positive evolution of AI. We first contrast notions of compliance in the ethical, legal, and technical fields; we outline both their differences and where they complement each other, with a particular focus on the roles of ethical charters, licenses, and technical documentation in these interactions. We then focus on the role of values in articulating the synergies between the fields and outline specific mechanisms of interaction between them in practice. We identify how these mechanisms have played out in several open governance fora: an open collaborative workshop, a responsible licensing initiative, and a proposed regulatory framework. By leveraging complementary notions of compliance in these three domains, we can create a more comprehensive framework for governing AI systems that jointly takes into account their technical capabilities, their impact on society, and how technical specifications can inform relevant regulations. Our analysis thus underlines the necessity of joint consideration of the ethical, legal, and technical in AI ethics frameworks to be used on a larger scale to govern AI systems and how the thinking in each of these areas can inform the others.

Major scandals in corporate history have urged the need for regulatory compliance, where organizations need to ensure that their controls (processes) comply with relevant laws, regulations, and policies. However, keeping track of the constantly changing legislation is difficult, thus organizations are increasingly adopting Regulatory Technology (RegTech) to facilitate the process. To this end, we introduce regulatory information retrieval (REG-IR), an application of document-to-document information retrieval (DOC2DOC IR), where the query is an entire document making the task more challenging than traditional IR where the queries are short. Furthermore, we compile and release two datasets based on the relationships between EU directives and UK legislation. We experiment on these datasets using a typical two-step pipeline approach comprising a pre-fetcher and a neural re-ranker. Experimenting with various pre-fetchers from BM25 to k nearest neighbors over representations from several BERT models, we show that fine-tuning a BERT model on an in-domain classification task produces the best representations for IR. We also show that neural re-rankers under-perform due to contradicting supervision, i.e., similar query-document pairs with opposite labels. Thus, they are biased towards the pre-fetcher's score. Interestingly, applying a date filter further improves the performance, showcasing the importance of the time dimension.

The human brain is a complex, dynamic network, which is commonly studied using functional magnetic resonance imaging (fMRI) and modeled as network of Regions of interest (ROIs) for understanding various brain functions. Recent studies utilize deep learning approaches to learn the brain network representation based on functional connectivity (FC) profile, broadly falling into two main categories. The Fixed-FC approaches, utilizing the FC profile which represents the linear temporal relation within the brain network, are limited by failing to capture informative brain temporal dynamics. On the other hand, the Dynamic-FC approaches, modeling the evolving FC profile over time, often exhibit less satisfactory performance due to challenges in handling the inherent noisy nature of fMRI data. To address these challenges, we propose Brain Masked Auto-Encoder (BrainMAE) for learning representations directly from fMRI time-series data. Our approach incorporates two essential components: a region-aware graph attention mechanism designed to capture the relationships between different brain ROIs, and a novel self-supervised masked autoencoding framework for effective model pre-training. These components enable the model to capture rich temporal dynamics of brain activity while maintaining resilience to inherent noise in fMRI data. Our experiments demonstrate that BrainMAE consistently outperforms established baseline methods by significant margins in four distinct downstream tasks. Finally, leveraging the model's inherent interpretability, our analysis of model-generated representations reveals findings that resonate with ongoing research in the field of neuroscience.

Survival prediction using whole slide images (WSIs) can be formulated as a multiple instance learning (MIL) problem. However, existing MIL methods often fail to explicitly capture pathological heterogeneity within WSIs, both globally -- through long-tailed morphological distributions, and locally through -- tile-level prediction uncertainty. Optimal transport (OT) provides a principled way of modeling such heterogeneity by incorporating marginal distribution constraints. Building on this insight, we propose OTSurv, a novel MIL framework from an optimal transport perspective. Specifically, OTSurv formulates survival predictions as a heterogeneity-aware OT problem with two constraints: (1) global long-tail constraint that models prior morphological distributions to avert both mode collapse and excessive uniformity by regulating transport mass allocation, and (2) local uncertainty-aware constraint that prioritizes high-confidence patches while suppressing noise by progressively raising the total transport mass. We then recast the initial OT problem, augmented by these constraints, into an unbalanced OT formulation that can be solved with an efficient, hardware-friendly matrix scaling algorithm. Empirically, OTSurv sets new state-of-the-art results across six popular benchmarks, achieving an absolute 3.6% improvement in average C-index. In addition, OTSurv achieves statistical significance in log-rank tests and offers high interpretability, making it a powerful tool for survival prediction in digital pathology. Our codes are available at https://github.com/Y-Research-SBU/OTSurv.

Regulatory texts are inherently long and complex, presenting significant challenges for information retrieval systems in supporting regulatory officers with compliance tasks. This paper introduces a hybrid information retrieval system that combines lexical and semantic search techniques to extract relevant information from large regulatory corpora. The system integrates a fine-tuned sentence transformer model with the traditional BM25 algorithm to achieve both semantic precision and lexical coverage. To generate accurate and comprehensive responses, retrieved passages are synthesized using Large Language Models (LLMs) within a Retrieval Augmented Generation (RAG) framework. Experimental results demonstrate that the hybrid system significantly outperforms standalone lexical and semantic approaches, with notable improvements in Recall@10 and MAP@10. By openly sharing our fine-tuned model and methodology, we aim to advance the development of robust natural language processing tools for compliance-driven applications in regulatory domains.

The ideal LLM content moderation system would be both structurally interpretable (so its decisions can be explained to users) and steerable (to reflect a community's values or align to safety standards). However, current systems fall short on both of these dimensions. To address this gap, we present SafetyAnalyst, a novel LLM safety moderation framework. Given a prompt, SafetyAnalyst creates a structured "harm-benefit tree," which identifies 1) the actions that could be taken if a compliant response were provided, 2) the harmful and beneficial effects of those actions (along with their likelihood, severity, and immediacy), and 3) the stakeholders that would be impacted by those effects. It then aggregates this structured representation into a harmfulness score based on a parameterized set of safety preferences, which can be transparently aligned to particular values. Using extensive harm-benefit features generated by SOTA LLMs on 19k prompts, we fine-tuned an open-weight LM to specialize in generating harm-benefit trees through symbolic knowledge distillation. On a comprehensive set of prompt safety benchmarks, we show that our system (average F1=0.75) outperforms existing LLM safety moderation systems (average F1<0.72) on prompt harmfulness classification, while offering the additional advantages of interpretability and steerability.

Deep clustering, which learns representation and semantic clustering without labels information, poses a great challenge for deep learning-based approaches. Despite significant progress in recent years, most existing methods focus on uniformly distributed datasets, significantly limiting the practical applicability of their methods. In this paper, we propose a more practical problem setting named deep imbalanced clustering, where the underlying classes exhibit an imbalance distribution. To address this challenge, we introduce a novel optimal transport-based pseudo-label learning framework. Our framework formulates pseudo-label generation as a Semantic-regularized Progressive Partial Optimal Transport (SP^2OT) problem, which progressively transports each sample to imbalanced clusters under several prior distribution and semantic relation constraints, thus generating high-quality and imbalance-aware pseudo-labels. To solve SP^2OT, we develop a Majorization-Minimization-based optimization algorithm. To be more precise, we employ the strategy of majorization to reformulate the SP^2OT problem into a Progressive Partial Optimal Transport problem, which can be transformed into an unbalanced optimal transport problem with augmented constraints and can be solved efficiently by a fast matrix scaling algorithm. Experiments on various datasets, including a human-curated long-tailed CIFAR100, challenging ImageNet-R, and large-scale subsets of fine-grained iNaturalist2018 datasets, demonstrate the superiority of our method.

Foundation models (FMs) provide societal benefits but also amplify risks. Governments, companies, and researchers have proposed regulatory frameworks, acceptable use policies, and safety benchmarks in response. However, existing public benchmarks often define safety categories based on previous literature, intuitions, or common sense, leading to disjointed sets of categories for risks specified in recent regulations and policies, which makes it challenging to evaluate and compare FMs across these benchmarks. To bridge this gap, we introduce AIR-Bench 2024, the first AI safety benchmark aligned with emerging government regulations and company policies, following the regulation-based safety categories grounded in our AI risks study, AIR 2024. AIR 2024 decomposes 8 government regulations and 16 company policies into a four-tiered safety taxonomy with 314 granular risk categories in the lowest tier. AIR-Bench 2024 contains 5,694 diverse prompts spanning these categories, with manual curation and human auditing to ensure quality. We evaluate leading language models on AIR-Bench 2024, uncovering insights into their alignment with specified safety concerns. By bridging the gap between public benchmarks and practical AI risks, AIR-Bench 2024 provides a foundation for assessing model safety across jurisdictions, fostering the development of safer and more responsible AI systems.

Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable foundation models that could possess dangerous capabilities sufficient to pose severe risks to public safety. Frontier AI models pose a distinct regulatory challenge: dangerous capabilities can arise unexpectedly; it is difficult to robustly prevent a deployed model from being misused; and, it is difficult to stop a model's capabilities from proliferating broadly. To address these challenges, at least three building blocks for the regulation of frontier models are needed: (1) standard-setting processes to identify appropriate requirements for frontier AI developers, (2) registration and reporting requirements to provide regulators with visibility into frontier AI development processes, and (3) mechanisms to ensure compliance with safety standards for the development and deployment of frontier AI models. Industry self-regulation is an important first step. However, wider societal discussions and government intervention will be needed to create standards and to ensure compliance with them. We consider several options to this end, including granting enforcement powers to supervisory authorities and licensure regimes for frontier AI models. Finally, we propose an initial set of safety standards. These include conducting pre-deployment risk assessments; external scrutiny of model behavior; using risk assessments to inform deployment decisions; and monitoring and responding to new information about model capabilities and uses post-deployment. We hope this discussion contributes to the broader conversation on how to balance public safety risks and innovation benefits from advances at the frontier of AI development.

The Right to Explanation and the Right to be Forgotten are two important principles outlined to regulate algorithmic decision making and data usage in real-world applications. While the right to explanation allows individuals to request an actionable explanation for an algorithmic decision, the right to be forgotten grants them the right to ask for their data to be deleted from all the databases and models of an organization. Intuitively, enforcing the right to be forgotten may trigger model updates which in turn invalidate previously provided explanations, thus violating the right to explanation. In this work, we investigate the technical implications arising due to the interference between the two aforementioned regulatory principles, and propose the first algorithmic framework to resolve the tension between them. To this end, we formulate a novel optimization problem to generate explanations that are robust to model updates due to the removal of training data instances by data deletion requests. We then derive an efficient approximation algorithm to handle the combinatorial complexity of this optimization problem. We theoretically demonstrate that our method generates explanations that are provably robust to worst-case data deletion requests with bounded costs in case of linear models and certain classes of non-linear models. Extensive experimentation with real-world datasets demonstrates the efficacy of the proposed framework.

With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety response framework designed to systematically safeguard LLMs at both the input and output levels. At the input level, the framework employs a supervised fine-tuning-based safety classification model. Through a fine-grained four-tier taxonomy (Safe, Unsafe, Conditionally Safe, Focused Attention), it performs precise risk identification and differentiated handling of user queries, significantly enhancing risk coverage and business scenario adaptability, and achieving a risk recall rate of 99.3%. At the output level, the framework integrates Retrieval-Augmented Generation (RAG) with a specifically fine-tuned interpretation model, ensuring all responses are grounded in a real-time, trustworthy knowledge base. This approach eliminates information fabrication and enables result traceability. Experimental results demonstrate that our proposed safety control model achieves a significantly higher safety score on public safety evaluation benchmarks compared to the baseline model, TinyR1-Safety-8B. Furthermore, on our proprietary high-risk test set, the framework's components attained a perfect 100% safety score, validating their exceptional protective capabilities in complex risk scenarios. This research provides an effective engineering pathway for building high-security, high-trust LLM applications.

This paper presents the system description of our entry for the COLING 2025 RegNLP RIRAG (Regulatory Information Retrieval and Answer Generation) challenge, focusing on leveraging advanced information retrieval and answer generation techniques in regulatory domains. We experimented with a combination of embedding models, including Stella, BGE, CDE, and Mpnet, and leveraged fine-tuning and reranking for retrieving relevant documents in top ranks. We utilized a novel approach, LeSeR, which achieved competitive results with a recall@10 of 0.8201 and map@10 of 0.6655 for retrievals. This work highlights the transformative potential of natural language processing techniques in regulatory applications, offering insights into their capabilities for implementing a retrieval augmented generation system while identifying areas for future improvement in robustness and domain adaptation.

This paper reviews Trustworthy Artificial Intelligence (TAI) and its various definitions. Considering the principles respected in any society, TAI is often characterized by a few attributes, some of which have led to confusion in regulatory or engineering contexts. We argue against using terms such as Responsible or Ethical AI as substitutes for TAI. And to help clarify any confusion, we suggest leaving them behind. Given the subjectivity and complexity inherent in TAI, developing a universal framework is deemed infeasible. Instead, we advocate for approaches centered on addressing key attributes and properties such as fairness, bias, risk, security, explainability, and reliability. We examine the ongoing regulatory landscape, with a focus on initiatives in the EU, China, and the USA. We recognize that differences in AI regulations based on geopolitical and geographical reasons pose an additional challenge for multinational companies. We identify risk as a core factor in AI regulation and TAI. For example, as outlined in the EU-AI Act, organizations must gauge the risk level of their AI products to act accordingly (or risk hefty fines). We compare modalities of TAI implementation and how multiple cross-functional teams are engaged in the overall process. Thus, a brute force approach for enacting TAI renders its efficiency and agility, moot. To address this, we introduce our framework Set-Formalize-Measure-Act (SFMA). Our solution highlights the importance of transforming TAI-aware metrics, drivers of TAI, stakeholders, and business/legal requirements into actual benchmarks or tests. Finally, over-regulation driven by panic of powerful AI models can, in fact, harm TAI too. Based on GitHub user-activity data, in 2023, AI open-source projects rose to top projects by contributor account. Enabling innovation in TAI hinges on the independent contributions of the open-source community.

Ensuring that Software Requirements Specifications (SRS) align with higher-level organizational or national requirements is vital, particularly in regulated environments such as finance and aerospace. In these domains, maintaining consistency, adhering to regulatory frameworks, minimizing errors, and meeting critical expectations are essential for the reliable functioning of systems. The widespread adoption of large language models (LLMs) highlights their immense potential, yet there remains considerable scope for improvement in retrieving relevant information and enhancing reasoning capabilities. This study demonstrates that integrating a robust Graph-RAG framework with advanced prompt engineering techniques, such as Chain of Thought and Tree of Thought, can significantly enhance performance. Compared to baseline RAG methods and simple prompting strategies, this approach delivers more accurate and context-aware results. While this method demonstrates significant improvements in performance, it comes with challenges. It is both costly and more complex to implement across diverse contexts, requiring careful adaptation to specific scenarios. Additionally, its effectiveness heavily relies on having complete and accurate input data, which may not always be readily available, posing further limitations to its scalability and practicality.

The global trade in electronic and electrical goods is complicated by the challenge of identifying e-waste, which is often misclassified to evade regulations. Traditional analysis methods struggle to discern the underlying patterns of this illicit trade within vast datasets. This research proposes and validates a robust, data-driven framework to segment products and identify goods exhibiting an anomalous "waste signature" a trade pattern defined by a clear 'inverse price-volume'. The core of the framework is an Outlier-Aware Segmentation method, an iterative K-Means approach that first isolates extreme outliers to prevent data skewing and then re-clusters the remaining products to reveal subtle market segments. To quantify risk, a "Waste Score" is developed using a Logistic Regression model that identifies products whose trade signatures are statistically similar to scrap. The findings reveal a consistent four-tier market hierarchy in both Malaysian and global datasets. A key pattern emerged from a comparative analysis: Malaysia's market structure is defined by high-volume bulk commodities, whereas the global market is shaped by high-value capital goods, indicating a unique national specialization. The framework successfully flags finished goods, such as electric generators (HS 8502), that are traded like scrap, providing a targeted list for regulatory scrutiny.

As a vital stage of automated rule checking (ARC), rule interpretation of regulatory texts requires considerable effort. However, interpreting regulatory clauses with implicit properties or complex computational logic is still challenging due to the lack of domain knowledge and limited expressibility of conventional logic representations. Thus, LLM-FuncMapper, an approach to identifying predefined functions needed to interpret various regulatory clauses based on the large language model (LLM), is proposed. First, by systematically analysis of building codes, a series of atomic functions are defined to capture shared computational logics of implicit properties and complex constraints, creating a database of common blocks for interpreting regulatory clauses. Then, a prompt template with the chain of thought is developed and further enhanced with a classification-based tuning strategy, to enable common LLMs for effective function identification. Finally, the proposed approach is validated with statistical analysis, experiments, and proof of concept. Statistical analysis reveals a long-tail distribution and high expressibility of the developed function database, with which almost 100% of computer-processible clauses can be interpreted and represented as computer-executable codes. Experiments show that LLM-FuncMapper achieve promising results in identifying relevant predefined functions for rule interpretation. Further proof of concept in automated rule interpretation also demonstrates the possibility of LLM-FuncMapper in interpreting complex regulatory clauses. To the best of our knowledge, this study is the first attempt to introduce LLM for understanding and interpreting complex regulatory clauses, which may shed light on further adoption of LLM in the construction domain.

Recent advances in large language models (LLMs) hold great promise for financial applications but introduce critical accuracy and compliance challenges in Digital Regulatory Reporting (DRR). To address these issues, we propose RKEFino1, a regulation knowledge-enhanced financial reasoning model built upon Fino1, fine-tuned with domain knowledge from XBRL, CDM, and MOF. We formulate two QA tasks-knowledge-based and mathematical reasoning-and introduce a novel Numerical NER task covering financial entities in both sentences and tables. Experimental results demonstrate the effectiveness and generalization capacity of RKEFino1 in compliance-critical financial tasks. We have released our model on Hugging Face.

Intelligent agents powered by large language models (LLMs) have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines. While their capabilities are promising, they also introduce novel vulnerabilities that demand careful consideration for safety. However, there exists a notable gap in the literature, as there has been no comprehensive exploration of these vulnerabilities. This position paper fills this gap by conducting a thorough examination of vulnerabilities in LLM-based agents within scientific domains, shedding light on potential risks associated with their misuse and emphasizing the need for safety measures. We begin by providing a comprehensive overview of the potential risks inherent to scientific LLM agents, taking into account user intent, the specific scientific domain, and their potential impact on the external environment. Then, we delve into the origins of these vulnerabilities and provide a scoping review of the limited existing works. Based on our analysis, we propose a triadic framework involving human regulation, agent alignment, and an understanding of environmental feedback (agent regulation) to mitigate these identified risks. Furthermore, we highlight the limitations and challenges associated with safeguarding scientific agents and advocate for the development of improved models, robust benchmarks, and comprehensive regulations to address these issues effectively.

The AI development community is increasingly making use of hosting intermediaries such as Hugging Face provide easy access to user-uploaded models and training data. These model marketplaces lower technical deployment barriers for hundreds of thousands of users, yet can be used in numerous potentially harmful and illegal ways. In this article, we explain ways in which AI systems, which can both `contain' content and be open-ended tools, present one of the trickiest platform governance challenges seen to date. We provide case studies of several incidents across three illustrative platforms -- Hugging Face, GitHub and Civitai -- to examine how model marketplaces moderate models. Building on this analysis, we outline important (and yet nevertheless limited) practices that industry has been developing to respond to moderation demands: licensing, access and use restrictions, automated content moderation, and open policy development. While the policy challenge at hand is a considerable one, we conclude with some ideas as to how platforms could better mobilize resources to act as a careful, fair, and proportionate regulatory access point.

Artificial intelligence (AI) systems will increasingly be used to cause harm as they grow more capable. In fact, AI systems are already starting to be used to automate fraudulent activities, violate human rights, create harmful fake images, and identify dangerous toxins. To prevent some misuses of AI, we argue that targeted interventions on certain capabilities will be warranted. These restrictions may include controlling who can access certain types of AI models, what they can be used for, whether outputs are filtered or can be traced back to their user, and the resources needed to develop them. We also contend that some restrictions on non-AI capabilities needed to cause harm will be required. Though capability restrictions risk reducing use more than misuse (facing an unfavorable Misuse-Use Tradeoff), we argue that interventions on capabilities are warranted when other interventions are insufficient, the potential harm from misuse is high, and there are targeted ways to intervene on capabilities. We provide a taxonomy of interventions that can reduce AI misuse, focusing on the specific steps required for a misuse to cause harm (the Misuse Chain), and a framework to determine if an intervention is warranted. We apply this reasoning to three examples: predicting novel toxins, creating harmful images, and automating spear phishing campaigns.

Our research endeavors to advance the concept of responsible artificial intelligence (AI), a topic of increasing importance within EU policy discussions. The EU has recently issued several publications emphasizing the necessity of trust in AI, underscoring the dual nature of AI as both a beneficial tool and a potential weapon. This dichotomy highlights the urgent need for international regulation. Concurrently, there is a need for frameworks that guide companies in AI development, ensuring compliance with such regulations. Our research aims to assist lawmakers and machine learning practitioners in navigating the evolving landscape of AI regulation, identifying focal areas for future attention. This paper introduces a comprehensive and, to our knowledge, the first unified definition of responsible AI. Through a structured literature review, we elucidate the current understanding of responsible AI. Drawing from this analysis, we propose an approach for developing a future framework centered around this concept. Our findings advocate for a human-centric approach to Responsible AI. This approach encompasses the implementation of AI methods with a strong emphasis on ethics, model explainability, and the pillars of privacy, security, and trust.

Cryptocurrencies have evolved into an important asset class, providing a variety of benefits. However, they also present significant risks, such as market volatility and the potential for misuse in illegal activities. These risks underline the urgent need for a comprehensive regulatory framework to ensure consumer protection, market integrity, and financial stability. Yet, the global landscape of cryptocurrency regulation remains complex, marked by substantial variations in regulatory frameworks among different countries. This paper aims to study these differences by investigating the regulatory landscapes across various jurisdictions. We first discuss regulatory challenges and considerations, and then conduct a comparative analysis of international regulatory stances, approaches, and measures. We hope our study offers practical insights to enhance the understanding of global trends in cryptocurrency regulation.

We present a framework for the automated measurement of responsible AI (RAI) metrics for large language models (LLMs) and associated products and services. Our framework for automatically measuring harms from LLMs builds on existing technical and sociotechnical expertise and leverages the capabilities of state-of-the-art LLMs, such as GPT-4. We use this framework to run through several case studies investigating how different LLMs may violate a range of RAI-related principles. The framework may be employed alongside domain-specific sociotechnical expertise to create measurements for new harm areas in the future. By implementing this framework, we aim to enable more advanced harm measurement efforts and further the responsible use of LLMs.

Aligning large language models (LLMs) with deployment-specific requirements is critical but inherently imperfect. Despite extensive training, models remain susceptible to misalignment and adversarial inputs such as jailbreaks. Content moderation filters are commonly used as external safeguards, though they typically focus narrowly on safety. We introduce SGM (Specification-Guided Moderation), a flexible framework for training moderation filters grounded in user-defined specifications that go beyond standard safety concerns. SGM automates training data generation without relying on human-written examples, enabling scalable support for diverse, application-specific alignment goals. SGM-trained filters perform on par with state-of-the-art safety filters built on curated datasets, while supporting fine-grained and user-defined alignment control.

Generative Foundation Models (GenFMs) have emerged as transformative tools. However, their widespread adoption raises critical concerns regarding trustworthiness across dimensions. This paper presents a comprehensive framework to address these challenges through three key contributions. First, we systematically review global AI governance laws and policies from governments and regulatory bodies, as well as industry practices and standards. Based on this analysis, we propose a set of guiding principles for GenFMs, developed through extensive multidisciplinary collaboration that integrates technical, ethical, legal, and societal perspectives. Second, we introduce TrustGen, the first dynamic benchmarking platform designed to evaluate trustworthiness across multiple dimensions and model types, including text-to-image, large language, and vision-language models. TrustGen leverages modular components--metadata curation, test case generation, and contextual variation--to enable adaptive and iterative assessments, overcoming the limitations of static evaluation methods. Using TrustGen, we reveal significant progress in trustworthiness while identifying persistent challenges. Finally, we provide an in-depth discussion of the challenges and future directions for trustworthy GenFMs, which reveals the complex, evolving nature of trustworthiness, highlighting the nuanced trade-offs between utility and trustworthiness, and consideration for various downstream applications, identifying persistent challenges and providing a strategic roadmap for future research. This work establishes a holistic framework for advancing trustworthiness in GenAI, paving the way for safer and more responsible integration of GenFMs into critical applications. To facilitate advancement in the community, we release the toolkit for dynamic evaluation.

Drug shortages pose critical risks to patient care and healthcare systems worldwide, yet the effectiveness of regulatory interventions remains poorly understood due to information asymmetries in pharmaceutical supply chains. We propose ShortageSim, addresses this challenge by providing the first simulation framework that evaluates the impact of regulatory interventions on competition dynamics under information asymmetry. Using Large Language Model (LLM)-based agents, the framework models the strategic decisions of drug manufacturers and institutional buyers, in response to shortage alerts given by the regulatory agency. Unlike traditional game theory models that assume perfect rationality and complete information, ShortageSim simulates heterogeneous interpretations on regulatory announcements and the resulting decisions. Experiments on self-processed dataset of historical shortage events show that ShortageSim reduces the resolution lag for production disruption cases by up to 84\%, achieving closer alignment to real-world trajectories than the zero-shot baseline. Our framework confirms the effect of regulatory alert in addressing shortages and introduces a new method for understanding competition in multi-stage environments under uncertainty. We open-source ShortageSim and a dataset of 2,925 FDA shortage events, providing a novel framework for future research on policy design and testing in supply chains under information asymmetry.

The EU's Artificial Intelligence Act (AI Act) is a significant step towards responsible AI development, but lacks clear technical interpretation, making it difficult to assess models' compliance. This work presents COMPL-AI, a comprehensive framework consisting of (i) the first technical interpretation of the EU AI Act, translating its broad regulatory requirements into measurable technical requirements, with the focus on large language models (LLMs), and (ii) an open-source Act-centered benchmarking suite, based on thorough surveying and implementation of state-of-the-art LLM benchmarks. By evaluating 12 prominent LLMs in the context of COMPL-AI, we reveal shortcomings in existing models and benchmarks, particularly in areas like robustness, safety, diversity, and fairness. This work highlights the need for a shift in focus towards these aspects, encouraging balanced development of LLMs and more comprehensive regulation-aligned benchmarks. Simultaneously, COMPL-AI for the first time demonstrates the possibilities and difficulties of bringing the Act's obligations to a more concrete, technical level. As such, our work can serve as a useful first step towards having actionable recommendations for model providers, and contributes to ongoing efforts of the EU to enable application of the Act, such as the drafting of the GPAI Code of Practice.

New capabilities in foundation models are owed in large part to massive, widely-sourced, and under-documented training data collections. Existing practices in data collection have led to challenges in documenting data transparency, tracing authenticity, verifying consent, privacy, representation, bias, copyright infringement, and the overall development of ethical and trustworthy foundation models. In response, regulation is emphasizing the need for training data transparency to understand foundation models' limitations. Based on a large-scale analysis of the foundation model training data landscape and existing solutions, we identify the missing infrastructure to facilitate responsible foundation model development practices. We examine the current shortcomings of common tools for tracing data authenticity, consent, and documentation, and outline how policymakers, developers, and data creators can facilitate responsible foundation model development by adopting universal data provenance standards.

As foundation models have accumulated hundreds of millions of users, developers have begun to take steps to prevent harmful types of uses. One salient intervention that foundation model developers adopt is acceptable use policies: legally binding policies that prohibit users from using a model for specific purposes. This paper identifies acceptable use policies from 30 foundation model developers, analyzes the use restrictions they contain, and argues that acceptable use policies are an important lens for understanding the regulation of foundation models. Taken together, developers' acceptable use policies include 127 distinct use restrictions; the wide variety in the number and type of use restrictions may create fragmentation across the AI supply chain. Developers also employ acceptable use policies to prevent competitors or specific industries from making use of their models. Developers alone decide what constitutes acceptable use, and rarely provide transparency about how they enforce their policies. In practice, acceptable use policies are difficult to enforce, and scrupulous enforcement can act as a barrier to researcher access and limit beneficial uses of foundation models. Nevertheless, acceptable use policies for foundation models are an early example of self-regulation that have a significant impact on the market for foundation models and the overall AI ecosystem.

We present LLM-KT, a flexible framework designed to enhance collaborative filtering (CF) models by seamlessly integrating LLM (Large Language Model)-generated features. Unlike existing methods that rely on passing LLM-generated features as direct inputs, our framework injects these features into an intermediate layer of any CF model, allowing the model to reconstruct and leverage the embeddings internally. This model-agnostic approach works with a wide range of CF models without requiring architectural changes, making it adaptable to various recommendation scenarios. Our framework is built for easy integration and modification, providing researchers and developers with a powerful tool for extending CF model capabilities through efficient knowledge transfer. We demonstrate its effectiveness through experiments on the MovieLens and Amazon datasets, where it consistently improves baseline CF models. Experimental studies showed that LLM-KT is competitive with the state-of-the-art methods in context-aware settings but can be applied to a broader range of CF models than current approaches.

The proliferation of harmful online content--e.g., toxicity, spam, and negative sentiment--demands robust and adaptable moderation systems. However, prevailing moderation systems are centralized and task-specific, offering limited transparency and neglecting diverse user preferences--an approach ill-suited for privacy-sensitive or decentralized environments. We propose a novel framework that leverages in-context learning (ICL) with foundation models to unify the detection of toxicity, spam, and negative sentiment across binary, multi-class, and multi-label settings. Crucially, our approach enables lightweight personalization, allowing users to easily block new categories, unblock existing ones, or extend detection to semantic variations through simple prompt-based interventions--all without model retraining. Extensive experiments on public benchmarks (TextDetox, UCI SMS, SST2) and a new, annotated Mastodon dataset reveal that: (i) foundation models achieve strong cross-task generalization, often matching or surpassing task-specific fine-tuned models; (ii) effective personalization is achievable with as few as one user-provided example or definition; and (iii) augmenting prompts with label definitions or rationales significantly enhances robustness to noisy, real-world data. Our work demonstrates a definitive shift beyond one-size-fits-all moderation, establishing ICL as a practical, privacy-preserving, and highly adaptable pathway for the next generation of user-centric content safety systems. To foster reproducibility and facilitate future research, we publicly release our code on GitHub and the annotated Mastodon dataset on Hugging Face.

Can foundation models be guided to execute tasks involving legal reasoning? We believe that building a benchmark to answer this question will require sustained collaborative efforts between the computer science and legal communities. To that end, this short paper serves three purposes. First, we describe how IRAC-a framework legal scholars use to distinguish different types of legal reasoning-can guide the construction of a Foundation Model oriented benchmark. Second, we present a seed set of 44 tasks built according to this framework. We discuss initial findings, and highlight directions for new tasks. Finally-inspired by the Open Science movement-we make a call for the legal and computer science communities to join our efforts by contributing new tasks. This work is ongoing, and our progress can be tracked here: https://github.com/HazyResearch/legalbench.

Generative AI (GAI) offers unprecedented opportunities for research and innovation, but its commercialization has raised concerns about transparency, reproducibility, and safety. Many open GAI models lack the necessary components for full understanding and reproducibility, and some use restrictive licenses whilst claiming to be ``open-source''. To address these concerns, we propose the Model Openness Framework (MOF), a ranked classification system that rates machine learning models based on their completeness and openness, following principles of open science, open source, open data, and open access. The MOF requires specific components of the model development lifecycle to be included and released under appropriate open licenses. This framework aims to prevent misrepresentation of models claiming to be open, guide researchers and developers in providing all model components under permissive licenses, and help individuals and organizations identify models that can be safely adopted without restrictions. By promoting transparency and reproducibility, the MOF combats ``openwashing'' practices and establishes completeness and openness as primary criteria alongside the core tenets of responsible AI. Wide adoption of the MOF will foster a more open AI ecosystem, benefiting research, innovation, and adoption of state-of-the-art models.

Scams exploiting real-time social engineering -- such as phishing, impersonation, and phone fraud -- remain a persistent and evolving threat across digital platforms. Existing defenses are largely reactive, offering limited protection during active interactions. We propose a privacy-preserving, AI-in-the-loop framework that proactively detects and disrupts scam conversations in real time. The system combines instruction-tuned artificial intelligence with a safety-aware utility function that balances engagement with harm minimization, and employs federated learning to enable continual model updates without raw data sharing. Experimental evaluations show that the system produces fluent and engaging responses (perplexity as low as 22.3, engagement approx0.80), while human studies confirm significant gains in realism, safety, and effectiveness over strong baselines. In federated settings, models trained with FedAvg sustain up to 30 rounds while preserving high engagement (approx0.80), strong relevance (approx0.74), and low PII leakage (leq0.0085). Even with differential privacy, novelty and safety remain stable, indicating that robust privacy can be achieved without sacrificing performance. The evaluation of guard models (LlamaGuard, LlamaGuard2/3, MD-Judge) shows a straightforward pattern: stricter moderation settings reduce the chance of exposing personal information, but they also limit how much the model engages in conversation. In contrast, more relaxed settings allow longer and richer interactions, which improve scam detection, but at the cost of higher privacy risk. To our knowledge, this is the first framework to unify real-time scam-baiting, federated privacy preservation, and calibrated safety moderation into a proactive defense paradigm.

This paper introduces ArGen (Auto-Regulation of Generative AI systems), a framework for aligning Large Language Models (LLMs) with complex sets of configurable, machine-readable rules spanning ethical principles, operational safety protocols, and regulatory compliance standards. Moving beyond just preference-based alignment, ArGen is designed to ensure LLMs adhere to these multifaceted policies through a novel synthesis of principle-based automated reward scoring, Group Relative Policy Optimisation (GRPO), and an Open Policy Agent (OPA) inspired governance layer. This approach provides the technical foundation for achieving and demonstrating compliance with diverse and nuanced governance requirements. To showcase the framework's capability to operationalize a deeply nuanced and culturally-specific value system, we present an in-depth case study: the development of a medical AI assistant guided by principles from Dharmic ethics (such as Ahimsa and Dharma), as derived from texts like the Bhagavad Gita. This challenging application demonstrates ArGen's adaptability, achieving a 70.9% improvement in domain-scope adherence over the baseline. Through our open-source repository, we show that ArGen's methodology offers a path to 'Governable Al' systems that are technically proficient, ethically robust, and verifiably compliant for safe deployment in diverse global contexts.

In this work, we propose an Automated Machine Learning (AutoML) system to search for models not only with good prediction accuracy but also fair. We first investigate the necessity and impact of unfairness mitigation in the AutoML context. We establish the FairAutoML framework. The framework provides a novel design based on pragmatic abstractions, which makes it convenient to incorporate existing fairness definitions, unfairness mitigation techniques, and hyperparameter search methods into the model search and evaluation process. Following this framework, we develop a fair AutoML system based on an existing AutoML system. The augmented system includes a resource allocation strategy to dynamically decide when and on which models to conduct unfairness mitigation according to the prediction accuracy, fairness, and resource consumption on the fly. Extensive empirical evaluation shows that our system can achieve a good `fair accuracy' and high resource efficiency.

The integration of Large Language Models (LLMs) into software engineering has revolutionized code generation, enabling unprecedented productivity through promptware and autonomous AI agents. However, this transformation introduces significant risks, including insecure code generation, hallucinated outputs, irreversible actions, and a lack of transparency and accountability. Incidents like the Replit database deletion underscore the urgent need for robust safety and governance mechanisms. This paper comprehensively analyzes the inherent challenges of LLM-assisted code generation, such as vulnerability inheritance, overtrust, misinterpretation, and the absence of standardized validation and rollback protocols. To address these, we propose the SAFE-AI Framework, a holistic approach emphasizing Safety, Auditability, Feedback, and Explainability. The framework integrates guardrails, sandboxing, runtime verification, risk-aware logging, human-in-the-loop systems, and explainable AI techniques to mitigate risks while fostering trust and compliance. We introduce a novel taxonomy of AI behaviors categorizing suggestive, generative, autonomous, and destructive actions to guide risk assessment and oversight. Additionally, we identify open problems, including the lack of standardized benchmarks for code specific hallucinations and autonomy levels, and propose future research directions for hybrid verification, semantic guardrails, and proactive governance tools. Through detailed comparisons of autonomy control, prompt engineering, explainability, and governance frameworks, this paper provides a roadmap for responsible AI integration in software engineering, aligning with emerging regulations like the EU AI Act and Canada's AIDA to ensure safe, transparent, and accountable AI-driven development.

We propose a novel machine learning approach for inferring causal variables of a target variable from observations. Our focus is on directly inferring a set of causal factors without requiring full causal graph reconstruction, which is computationally challenging in large-scale systems. The identified causal set consists of all potential regulators of the target variable under experimental settings, enabling efficient regulation when intervention costs and feasibility vary across variables. To achieve this, we train a neural network using supervised learning on simulated data to infer causality. By employing a local-inference strategy, our approach scales with linear complexity in the number of variables, efficiently scaling up to thousands of variables. Empirical results demonstrate superior performance in identifying causal relationships within large-scale gene regulatory networks, outperforming existing methods that emphasize full-graph discovery. We validate our model's generalization capability across out-of-distribution graph structures and generating mechanisms, including gene regulatory networks of E. coli and the human K562 cell line. Implementation codes are available at https://github.com/snu-mllab/Targeted-Cause-Discovery.

One concern with the rise of large language models lies with their potential for significant harm, particularly from pretraining on biased, obscene, copyrighted, and private information. Emerging ethical approaches have attempted to filter pretraining material, but such approaches have been ad hoc and failed to take context into account. We offer an approach to filtering grounded in law, which has directly addressed the tradeoffs in filtering material. First, we gather and make available the Pile of Law, a 256GB (and growing) dataset of open-source English-language legal and administrative data, covering court opinions, contracts, administrative rules, and legislative records. Pretraining on the Pile of Law may help with legal tasks that have the promise to improve access to justice. Second, we distill the legal norms that governments have developed to constrain the inclusion of toxic or private content into actionable lessons for researchers and discuss how our dataset reflects these norms. Third, we show how the Pile of Law offers researchers the opportunity to learn such filtering rules directly from the data, providing an exciting new research direction in model-based processing.

Regulatory documents, issued by governmental regulatory bodies, establish rules, guidelines, and standards that organizations must adhere to for legal compliance. These documents, characterized by their length, complexity and frequent updates, are challenging to interpret, requiring significant allocation of time and expertise on the part of organizations to ensure ongoing compliance.Regulatory Natural Language Processing (RegNLP) is a multidisciplinary subfield aimed at simplifying access to and interpretation of regulatory rules and obligations. We define an Automated Question-Passage Generation task for RegNLP, create the ObliQA dataset containing 27,869 questions derived from the Abu Dhabi Global Markets (ADGM) financial regulation document collection, design a baseline Regulatory Information Retrieval and Answer Generation system, and evaluate it with RePASs, a novel evaluation metric that tests whether generated answers accurately capture all relevant obligations and avoid contradictions.

Most safety testing efforts for large language models (LLMs) today focus on evaluating foundation models. However, there is a growing need to evaluate safety at the application level, as components such as system prompts, retrieval pipelines, and guardrails introduce additional factors that significantly influence the overall safety of LLM applications. In this paper, we introduce a practical framework for evaluating application-level safety in LLM systems, validated through real-world deployment across multiple use cases within our organization. The framework consists of two parts: (1) principles for developing customized safety risk taxonomies, and (2) practices for evaluating safety risks in LLM applications. We illustrate how the proposed framework was applied in our internal pilot, providing a reference point for organizations seeking to scale their safety testing efforts. This work aims to bridge the gap between theoretical concepts in AI safety and the operational realities of safeguarding LLM applications in practice, offering actionable guidance for safe and scalable deployment.

Ensuring compliance with international data protection standards for privacy and data security is a crucial but complex task, often requiring substantial legal expertise. This paper introduces LegiLM, a novel legal language model specifically tailored for consulting on data or information compliance. LegiLM leverages a pre-trained GDPR Fines dataset and has been fine-tuned to automatically assess whether particular actions or events breach data security and privacy regulations. By incorporating a specialized dataset that includes global data protection laws, meticulously annotated policy documents, and relevant privacy policies, LegiLM is optimized for addressing data compliance challenges. The model integrates advanced legal reasoning methods and information retrieval enhancements to enhance accuracy and reliability in practical legal consulting scenarios. Our evaluation using a custom benchmark dataset demonstrates that LegiLM excels in detecting data regulation breaches, offering sound legal justifications, and recommending necessary compliance modifications, setting a new benchmark for AI-driven legal compliance solutions. Our resources are publicly available at https://github.com/DAOLegalAI/LegiLM

Financial institutions deploy Large Language Models (LLMs) for reconciliations, regulatory reporting, and client communications, but nondeterministic outputs (output drift) undermine auditability and trust. We quantify drift across five model architectures (7B-120B parameters) on regulated financial tasks, revealing a stark inverse relationship: smaller models (Granite-3-8B, Qwen2.5-7B) achieve 100% output consistency at T=0.0, while GPT-OSS-120B exhibits only 12.5% consistency (95% CI: 3.5-36.0%) regardless of configuration (p<0.0001, Fisher's exact test). This finding challenges conventional assumptions that larger models are universally superior for production deployment. Our contributions include: (i) a finance-calibrated deterministic test harness combining greedy decoding (T=0.0), fixed seeds, and SEC 10-K structure-aware retrieval ordering; (ii) task-specific invariant checking for RAG, JSON, and SQL outputs using finance-calibrated materiality thresholds (plus or minus 5%) and SEC citation validation; (iii) a three-tier model classification system enabling risk-appropriate deployment decisions; and (iv) an audit-ready attestation system with dual-provider validation. We evaluated five models (Qwen2.5-7B via Ollama, Granite-3-8B via IBM watsonx.ai, Llama-3.3-70B, Mistral-Medium-2505, and GPT-OSS-120B) across three regulated financial tasks. Across 480 runs (n=16 per condition), structured tasks (SQL) remain stable even at T=0.2, while RAG tasks show drift (25-75%), revealing task-dependent sensitivity. Cross-provider validation confirms deterministic behavior transfers between local and cloud deployments. We map our framework to Financial Stability Board (FSB), Bank for International Settlements (BIS), and Commodity Futures Trading Commission (CFTC) requirements, demonstrating practical pathways for compliance-ready AI deployments.

Legal contracts in the custody and fund services domain govern critical aspects such as key provider responsibilities, fee schedules, and indemnification rights. However, it is challenging for an off-the-shelf Large Language Model (LLM) to ingest these contracts due to the lengthy unstructured streams of text, limited LLM context windows, and complex legal jargon. To address these challenges, we introduce LAW (Legal Agentic Workflows for Custody and Fund Services Contracts). LAW features a modular design that responds to user queries by orchestrating a suite of domain-specific tools and text agents. Our experiments demonstrate that LAW, by integrating multiple specialized agents and tools, significantly outperforms the baseline. LAW excels particularly in complex tasks such as calculating a contract's termination date, surpassing the baseline by 92.9% points. Furthermore, LAW offers a cost-effective alternative to traditional fine-tuned legal LLMs by leveraging reusable, domain-specific tools.

This paper introduces a multifaceted methodology for fine-tuning and evaluating large language models (LLMs) for specialized monetization tasks. The goal is to balance general language proficiency with domain-specific skills. The methodology has three main components: 1) Carefully blending in-domain and general-purpose data during fine-tuning to achieve an optimal balance between general and specialized capabilities; 2) Designing a comprehensive evaluation framework with 45 questions tailored to assess performance on functionally relevant dimensions like reliability, consistency, and business impact; 3) Analyzing how model size and continual training influence metrics to guide efficient resource allocation during fine-tuning. The paper details the design, data collection, analytical techniques, and results validating the proposed frameworks. It aims to provide businesses and researchers with actionable insights on effectively adapting LLMs for specialized contexts. We also intend to make public the comprehensive evaluation framework, which includes the 45 tailored questions and their respective scoring guidelines, to foster transparency and collaboration in adapting LLMs for specialized tasks.

Through a systematic review of academic literature, we propose a taxonomy of systemic risks associated with artificial intelligence (AI), in particular general-purpose AI. Following the EU AI Act's definition, we consider systemic risks as large-scale threats that can affect entire societies or economies. Starting with an initial pool of 1,781 documents, we analyzed 86 selected papers to identify 13 categories of systemic risks and 50 contributing sources. Our findings reveal a complex landscape of potential threats, ranging from environmental harm and structural discrimination to governance failures and loss of control. Key sources of systemic risk emerge from knowledge gaps, challenges in recognizing harm, and the unpredictable trajectory of AI development. The taxonomy provides a snapshot of current academic literature on systemic risks. This paper contributes to AI safety research by providing a structured groundwork for understanding and addressing the potential large-scale negative societal impacts of general-purpose AI. The taxonomy can inform policymakers in risk prioritization and regulatory development.

The prevalence of multi-modal content on social media complicates automated moderation strategies. This calls for an enhancement in multi-modal classification and a deeper understanding of understated meanings in images and memes. Although previous efforts have aimed at improving model performance through fine-tuning, few have explored an end-to-end optimization pipeline that accounts for modalities, prompting, labeling, and fine-tuning. In this study, we propose an end-to-end conceptual framework for model optimization in complex tasks. Experiments support the efficacy of this traditional yet novel framework, achieving the highest accuracy and AUROC. Ablation experiments demonstrate that isolated optimizations are not ineffective on their own.

Trustworthy Artificial Intelligence (AI) is based on seven technical requirements sustained over three main pillars that should be met throughout the system's entire life cycle: it should be (1) lawful, (2) ethical, and (3) robust, both from a technical and a social perspective. However, attaining truly trustworthy AI concerns a wider vision that comprises the trustworthiness of all processes and actors that are part of the system's life cycle, and considers previous aspects from different lenses. A more holistic vision contemplates four essential axes: the global principles for ethical use and development of AI-based systems, a philosophical take on AI ethics, a risk-based approach to AI regulation, and the mentioned pillars and requirements. The seven requirements (human agency and oversight; robustness and safety; privacy and data governance; transparency; diversity, non-discrimination and fairness; societal and environmental wellbeing; and accountability) are analyzed from a triple perspective: What each requirement for trustworthy AI is, Why it is needed, and How each requirement can be implemented in practice. On the other hand, a practical approach to implement trustworthy AI systems allows defining the concept of responsibility of AI-based systems facing the law, through a given auditing process. Therefore, a responsible AI system is the resulting notion we introduce in this work, and a concept of utmost necessity that can be realized through auditing processes, subject to the challenges posed by the use of regulatory sandboxes. Our multidisciplinary vision of trustworthy AI culminates in a debate on the diverging views published lately about the future of AI. Our reflections in this matter conclude that regulation is a key for reaching a consensus among these views, and that trustworthy and responsible AI systems will be crucial for the present and future of our society.

This paper investigates the application of Deep Reinforcement Learning (DRL) for Environment, Social, and Governance (ESG) financial portfolio management, with a specific focus on the potential benefits of ESG score-based market regulation. We leveraged an Advantage Actor-Critic (A2C) agent and conducted our experiments using environments encoded within the OpenAI Gym, adapted from the FinRL platform. The study includes a comparative analysis of DRL agent performance under standard Dow Jones Industrial Average (DJIA) market conditions and a scenario where returns are regulated in line with company ESG scores. In the ESG-regulated market, grants were proportionally allotted to portfolios based on their returns and ESG scores, while taxes were assigned to portfolios below the mean ESG score of the index. The results intriguingly reveal that the DRL agent within the ESG-regulated market outperforms the standard DJIA market setup. Furthermore, we considered the inclusion of ESG variables in the agent state space, and compared this with scenarios where such data were excluded. This comparison adds to the understanding of the role of ESG factors in portfolio management decision-making. We also analyze the behaviour of the DRL agent in IBEX 35 and NASDAQ-100 indexes. Both the A2C and Proximal Policy Optimization (PPO) algorithms were applied to these additional markets, providing a broader perspective on the generalization of our findings. This work contributes to the evolving field of ESG investing, suggesting that market regulation based on ESG scoring can potentially improve DRL-based portfolio management, with significant implications for sustainable investing strategies.

Harm reporting in Artificial Intelligence (AI) currently lacks a structured process for disclosing and addressing algorithmic flaws, relying largely on an ad-hoc approach. This contrasts sharply with the well-established Coordinated Vulnerability Disclosure (CVD) ecosystem in software security. While global efforts to establish frameworks for AI transparency and collaboration are underway, the unique challenges presented by machine learning (ML) models demand a specialized approach. To address this gap, we propose implementing a Coordinated Flaw Disclosure (CFD) framework tailored to the complexities of ML and AI issues. This paper reviews the evolution of ML disclosure practices, from ad hoc reporting to emerging participatory auditing methods, and compares them with cybersecurity norms. Our framework introduces innovations such as extended model cards, dynamic scope expansion, an independent adjudication panel, and an automated verification process. We also outline a forthcoming real-world pilot of CFD. We argue that CFD could significantly enhance public trust in AI systems. By balancing organizational and community interests, CFD aims to improve AI accountability in a rapidly evolving technological landscape.

The rapid evolution of generative AI has expanded the breadth of risks associated with AI systems. While various taxonomies and frameworks exist to classify these risks, the lack of interoperability between them creates challenges for researchers, practitioners, and policymakers seeking to operationalise AI governance. To address this gap, we introduce the AI Risk Atlas, a structured taxonomy that consolidates AI risks from diverse sources and aligns them with governance frameworks. Additionally, we present the Risk Atlas Nexus, a collection of open-source tools designed to bridge the divide between risk definitions, benchmarks, datasets, and mitigation strategies. This knowledge-driven approach leverages ontologies and knowledge graphs to facilitate risk identification, prioritization, and mitigation. By integrating AI-assisted compliance workflows and automation strategies, our framework lowers the barrier to responsible AI adoption. We invite the broader research and open-source community to contribute to this evolving initiative, fostering cross-domain collaboration and ensuring AI governance keeps pace with technological advancements.

There is increasing attention being given to how to regulate AI systems. As governing bodies grapple with what values to encapsulate into regulation, we consider the technical half of the question: To what extent can AI experts vet an AI system for adherence to regulatory requirements? We investigate this question through two public sector procurement checklists, identifying what we can do now, what we should be able to do with technical innovation in AI, and what requirements necessitate a more interdisciplinary approach.

Retrieval-Augmented Generation (RAG) based on Large Language Models (LLMs) is a powerful solution to understand and query the industry's closed-source documents. However, basic RAG often struggles with complex QA tasks in legal and regulatory domains, particularly when dealing with numerous government documents. The top-k strategy frequently misses golden chunks, leading to incomplete or inaccurate answers. To address these retrieval bottlenecks, we explore two strategies to improve evidence coverage and answer quality. The first is a One-SHOT retrieval method that adaptively selects chunks based on a token budget, allowing as much relevant content as possible to be included within the model's context window. Additionally, we design modules to further filter and refine the chunks. The second is an iterative retrieval strategy built on a Reasoning Agentic RAG framework, where a reasoning LLM dynamically issues search queries, evaluates retrieved results, and progressively refines the context over multiple turns. We identify query drift and retrieval laziness issues and further design two modules to tackle them. Through extensive experiments on a dataset of government documents, we aim to offer practical insights and guidance for real-world applications in legal and regulatory domains.

Open-source AI libraries are foundational to modern AI systems but pose significant, underexamined risks across security, licensing, maintenance, supply chain integrity, and regulatory compliance. We present LibVulnWatch, a graph-based agentic assessment framework that performs deep, source-grounded evaluations of these libraries. Built on LangGraph, the system coordinates a directed acyclic graph of specialized agents to extract, verify, and quantify risk using evidence from trusted sources such as repositories, documentation, and vulnerability databases. LibVulnWatch generates reproducible, governance-aligned scores across five critical domains, publishing them to a public leaderboard for longitudinal ecosystem monitoring. Applied to 20 widely used libraries, including ML frameworks, LLM inference engines, and agent orchestration tools, our system covers up to 88% of OpenSSF Scorecard checks while uncovering up to 19 additional risks per library. These include critical Remote Code Execution (RCE) vulnerabilities, absent Software Bills of Materials (SBOMs), licensing constraints, undocumented telemetry, and widespread gaps in regulatory documentation and auditability. By translating high-level governance principles into practical, verifiable metrics, LibVulnWatch advances technical AI governance with a scalable, transparent mechanism for continuous supply chain risk assessment and informed library selection.

The rapid growth of the financial sector and the rising focus on Environmental, Social, and Governance (ESG) considerations highlight the need for advanced NLP tools. However, open-source LLMs proficient in both finance and ESG domains remain scarce. To address this gap, we introduce SusGen-30K, a category-balanced dataset comprising seven financial NLP tasks and ESG report generation, and propose TCFD-Bench, a benchmark for evaluating sustainability report generation. Leveraging this dataset, we developed SusGen-GPT, a suite of models achieving state-of-the-art performance across six adapted and two off-the-shelf tasks, trailing GPT-4 by only 2% despite using 7-8B parameters compared to GPT-4's 1,700B. Based on this, we propose the SusGen system, integrated with Retrieval-Augmented Generation (RAG), to assist in sustainability report generation. This work demonstrates the efficiency of our approach, advancing research in finance and ESG.

Telecom networks are becoming increasingly complex, with diversified deployment scenarios, multi-standards, and multi-vendor support. The intricate nature of the telecom network ecosystem presents challenges to effectively manage, operate, and optimize networks. To address these hurdles, Artificial Intelligence (AI) has been widely adopted to solve different tasks in telecom networks. However, these conventional AI models are often designed for specific tasks, rely on extensive and costly-to-collect labeled data that require specialized telecom expertise for development and maintenance. The AI models usually fail to generalize and support diverse deployment scenarios and applications. In contrast, Foundation Models (FMs) show effective generalization capabilities in various domains in language, vision, and decision-making tasks. FMs can be trained on multiple data modalities generated from the telecom ecosystem and leverage specialized domain knowledge. Moreover, FMs can be fine-tuned to solve numerous specialized tasks with minimal task-specific labeled data and, in some instances, are able to leverage context to solve previously unseen problems. At the dawn of 6G, this paper investigates the potential opportunities of using FMs to shape the future of telecom technologies and standards. In particular, the paper outlines a conceptual process for developing Telecom FMs (TFMs) and discusses emerging opportunities for orchestrating specialized TFMs for network configuration, operation, and maintenance. Finally, the paper discusses the limitations and challenges of developing and deploying TFMs.

Transformer-based architectures are widely adopted in sequential recommendation systems, yet their application in Financial Services (FS) presents distinct practical and modeling challenges for real-time recommendation. These include:a) long-range user interactions (implicit and explicit) spanning both digital and physical channels generating temporally heterogeneous context, b) the presence of multiple interrelated products require coordinated models to support varied ad placements and personalized feeds, while balancing competing business goals. We propose FinTRec, a transformer-based framework that addresses these challenges and its operational objectives in FS. While tree-based models have traditionally been preferred in FS due to their explainability and alignment with regulatory requirements, our study demonstrate that FinTRec offers a viable and effective shift toward transformer-based architectures. Through historic simulation and live A/B test correlations, we show FinTRec consistently outperforms the production-grade tree-based baseline. The unified architecture, when fine-tuned for product adaptation, enables cross-product signal sharing, reduces training cost and technical debt, while improving offline performance across all products. To our knowledge, this is the first comprehensive study of unified sequential recommendation modeling in FS that addresses both technical and business considerations.

Vanilla Federated learning (FL) relies on the centralized global aggregation mechanism and assumes that all clients are honest. This makes it a challenge for FL to alleviate the single point of failure and dishonest clients. These impending challenges in the design philosophy of FL call for blockchain-based federated learning (BFL) due to the benefits of coupling FL and blockchain (e.g., democracy, incentive, and immutability). However, one problem in vanilla BFL is that its capabilities do not follow adopters' needs in a dynamic fashion. Besides, vanilla BFL relies on unverifiable clients' self-reported contributions like data size because checking clients' raw data is not allowed in FL for privacy concerns. We design and evaluate a novel BFL framework, and resolve the identified challenges in vanilla BFL with greater flexibility and incentive mechanism called FAIR-BFL. In contrast to existing works, FAIR-BFL offers unprecedented flexibility via the modular design, allowing adopters to adjust its capabilities following business demands in a dynamic fashion. Our design accounts for BFL's ability to quantify each client's contribution to the global learning process. Such quantification provides a rational metric for distributing the rewards among federated clients and helps discover malicious participants that may poison the global model.

We develop a data-driven deep neural operator framework to approximate multiple output states for a diesel engine and generate real-time predictions with reasonable accuracy. As emission norms become more stringent, the need for fast and accurate models that enable analysis of system behavior have become an essential requirement for system development. The fast transient processes involved in the operation of a combustion engine make it difficult to develop accurate physics-based models for such systems. As an alternative to physics based models, we develop an operator-based regression model (DeepONet) to learn the relevant output states for a mean-value gas flow engine model using the engine operating conditions as input variables. We have adopted a mean-value model as a benchmark for comparison, simulated using Simulink. The developed approach necessitates using the initial conditions of the output states to predict the accurate sequence over the temporal domain. To this end, a sequence-to-sequence approach is embedded into the proposed framework. The accuracy of the model is evaluated by comparing the prediction output to ground truth generated from Simulink model. The maximum mathcal L_2 relative error observed was approximately 6.5%. The sensitivity of the DeepONet model is evaluated under simulated noise conditions and the model shows relatively low sensitivity to noise. The uncertainty in model prediction is further assessed by using a mean ensemble approach. The worst-case error at the (mu + 2sigma) boundary was found to be 12%. The proposed framework provides the ability to predict output states in real-time and enables data-driven learning of complex input-output operator mapping. As a result, this model can be applied during initial development stages, where accurate models may not be available.

We present MixtureVitae, an open-access pretraining corpus built to minimize legal risk while providing strong model performance. MixtureVitae follows a risk-mitigated sourcing strategy that combines public-domain and permissively licensed text (e.g., CC-BY/Apache) with carefully justified low-risk additions (e.g., government works and EU TDM-eligible sources), alongside targeted instruction, reasoning and synthetic data with documented provenance. We detail a transparent, multi-stage pipeline for license-aware filtering, safety and quality screening, and domain-aware mixing, and we release the dataset and curation recipes to support reproducible research. In controlled experiments using the open-sci-ref training protocol (fixed architectures at 130M/400M/1.3B/1.7B parameters; training budgets of 50B and 300B tokens), models trained on MixtureVitae consistently outperform other permissive datasets across a suite of standard benchmarks, and at the 1.7B/300B setting they surpass FineWeb-Edu and approach DCLM in the later stages of training. Performance is particularly strong on math/code and competitive on QA tasks. These results demonstrate that permissive-first, risk-mitigated data provides a practical and legally mitigated foundation for training capable LLMs, reducing reliance on indiscriminate web scraping without sacrificing competitiveness. Code: https://github.com/ontocord/mixturevitae

Large language models (LLMs), including both proprietary and open-source models, have showcased remarkable capabilities in addressing a wide range of downstream tasks. Nonetheless, when it comes to practical Chinese legal tasks, these models fail to meet the actual requirements. Proprietary models do not ensure data privacy for sensitive legal cases, while open-source models demonstrate unsatisfactory performance due to their lack of legal knowledge. To address this problem, we introduce LawGPT, the first open-source model specifically designed for Chinese legal applications. LawGPT comprises two key components: legal-oriented pre-training and legal supervised fine-tuning. Specifically, we employ large-scale Chinese legal documents for legal-oriented pre-training to incorporate legal domain knowledge. To further improve the model's performance on downstream legal tasks, we create a knowledge-driven instruction dataset for legal supervised fine-tuning. Our experimental results demonstrate that LawGPT outperforms the open-source LLaMA 7B model. Our code and resources are publicly available at https://github.com/pengxiao-song/LaWGPT and have received 5.7K stars on GitHub.

We present a comprehensive AI risk taxonomy derived from eight government policies from the European Union, United States, and China and 16 company policies worldwide, making a significant step towards establishing a unified language for generative AI safety evaluation. We identify 314 unique risk categories organized into a four-tiered taxonomy. At the highest level, this taxonomy encompasses System & Operational Risks, Content Safety Risks, Societal Risks, and Legal & Rights Risks. The taxonomy establishes connections between various descriptions and approaches to risk, highlighting the overlaps and discrepancies between public and private sector conceptions of risk. By providing this unified framework, we aim to advance AI safety through information sharing across sectors and the promotion of best practices in risk mitigation for generative AI models and systems.

This paper argues that market governance mechanisms should be considered a key approach in the governance of artificial intelligence (AI), alongside traditional regulatory frameworks. While current governance approaches have predominantly focused on regulation, we contend that market-based mechanisms offer effective incentives for responsible AI development. We examine four emerging vectors of market governance: insurance, auditing, procurement, and due diligence, demonstrating how these mechanisms can affirm the relationship between AI risk and financial risk while addressing capital allocation inefficiencies. While we do not claim that market forces alone can adequately protect societal interests, we maintain that standardised AI disclosures and market mechanisms can create powerful incentives for safe and responsible AI development. This paper urges regulators, economists, and machine learning researchers to investigate and implement market-based approaches to AI governance.

Regulatory compliance auditing across diverse industrial domains requires heightened quality assurance and traceability. Present manual and intermittent approaches to such auditing yield significant challenges, potentially leading to oversights in the monitoring process. To address these issues, we introduce a real-time, multi-modal sensing system employing 3D time-of-flight and RGB cameras, coupled with unsupervised learning techniques on edge AI devices. This enables continuous object tracking thereby enhancing efficiency in record-keeping and minimizing manual interventions. While we validate the system in a knife sanitization context within agrifood facilities, emphasizing its prowess against occlusion and low-light issues with RGB cameras, its potential spans various industrial monitoring settings.

Risk management in finance involves recognizing, evaluating, and addressing financial risks to maintain stability and ensure regulatory compliance. Extracting relevant insights from extensive regulatory documents is a complex challenge requiring advanced retrieval and language models. This paper introduces RiskData, a dataset specifically curated for finetuning embedding models in risk management, and RiskEmbed, a finetuned embedding model designed to improve retrieval accuracy in financial question-answering systems. The dataset is derived from 94 regulatory guidelines published by the Office of the Superintendent of Financial Institutions (OSFI) from 1991 to 2024. We finetune a state-of-the-art sentence BERT embedding model to enhance domain-specific retrieval performance typically for Retrieval-Augmented Generation (RAG) systems. Experimental results demonstrate that RiskEmbed significantly outperforms general-purpose and financial embedding models, achieving substantial improvements in ranking metrics. By open-sourcing both the dataset and the model, we provide a valuable resource for financial institutions and researchers aiming to develop more accurate and efficient risk management AI solutions.

Federated Domain Adaptation (FDA) describes the federated learning (FL) setting where source clients and a server work collaboratively to improve the performance of a target client where limited data is available. The domain shift between the source and target domains, coupled with limited data of the target client, makes FDA a challenging problem, e.g., common techniques such as federated averaging and fine-tuning fail due to domain shift and data scarcity. To theoretically understand the problem, we introduce new metrics that characterize the FDA setting and a theoretical framework with novel theorems for analyzing the performance of server aggregation rules. Further, we propose a novel lightweight aggregation rule, Federated Gradient Projection (FedGP), which significantly improves the target performance with domain shift and data scarcity. Moreover, our theory suggests an auto-weighting scheme that finds the optimal combinations of the source and target gradients. This scheme improves both FedGP and a simpler heuristic aggregation rule. Extensive experiments verify the theoretical insights and illustrate the effectiveness of the proposed methods in practice.

This paper introduces the Hazard-Aware System Card (HASC), a novel framework designed to enhance transparency and accountability in the development and deployment of AI systems. The HASC builds upon existing model card and system card concepts by integrating a comprehensive, dynamic record of an AI system's security and safety posture. The framework proposes a standardized system of identifiers, including a novel AI Safety Hazard (ASH) ID, to complement existing security identifiers like CVEs, allowing for clear and consistent communication of fixed flaws. By providing a single, accessible source of truth, the HASC empowers developers and stakeholders to make more informed decisions about AI system safety throughout its lifecycle. Ultimately, we also compare our proposed AI system cards with the ISO/IEC 42001:2023 standard and discuss how they can be used to complement each other, providing greater transparency and accountability for AI systems.

Watermarking has emerged as a leading technical proposal for attributing generative AI content and is increasingly cited in global governance frameworks. This paper argues that current implementations risk serving as symbolic compliance rather than delivering effective oversight. We identify a growing gap between regulatory expectations and the technical limitations of existing watermarking schemes. Through analysis of policy proposals and industry practices, we show how incentive structures disincentivize robust, auditable deployments. To realign watermarking with governance goals, we propose a three-layer framework encompassing technical standards, audit infrastructure, and enforcement mechanisms. Without enforceable requirements and independent verification, watermarking will remain inadequate for accountability and ultimately undermine broader efforts in AI safety and regulation.

Automatic Compliance Checking (ACC) within the Architecture, Engineering, and Construction (AEC) sector necessitates automating the interpretation of building regulations to achieve its full potential. However, extracting information from textual rules to convert them to a machine-readable format has been a challenge due to the complexities associated with natural language and the limited resources that can support advanced machine-learning techniques. To address this challenge, we introduce CODE-ACCORD, a unique dataset compiled under the EU Horizon ACCORD project. CODE-ACCORD comprises 862 self-contained sentences extracted from the building regulations of England and Finland. Aligned with our core objective of facilitating information extraction from text for machine-readable rule generation, each sentence was annotated with entities and relations. Entities represent specific components such as "window" and "smoke detectors", while relations denote semantic associations between these entities, collectively capturing the conveyed ideas in natural language. We manually annotated all the sentences using a group of 12 annotators. Each sentence underwent annotations by multiple annotators and subsequently careful data curation to finalise annotations, ensuring their accuracy and reliability, thereby establishing the dataset as a solid ground truth. CODE-ACCORD offers a rich resource for diverse machine learning and natural language processing (NLP) related tasks in ACC, including text classification, entity recognition and relation extraction. To the best of our knowledge, this is the first entity and relation-annotated dataset in compliance checking, which is also publicly available.

The rapid advancement of ML models in critical sectors such as healthcare, finance, and security has intensified the need for robust data security, model integrity, and reliable outputs. Large multimodal foundational models, while crucial for complex tasks, present challenges in scalability, reliability, and potential misuse. Decentralized systems offer a solution by distributing workload and mitigating central points of failure, but they introduce risks of unauthorized access to sensitive data across nodes. We address these challenges with a comprehensive framework designed for responsible AI development. Our approach incorporates: 1) Zero-knowledge proofs for secure model verification, enhancing trust without compromising privacy. 2) Consensus-based verification checks to ensure consistent outputs across nodes, mitigating hallucinations and maintaining model integrity. 3) Split Learning techniques that segment models across different nodes, preserving data privacy by preventing full data access at any point. 4) Hardware-based security through trusted execution environments (TEEs) to protect data and computations. This framework aims to enhance security and privacy and improve the reliability and fairness of multimodal AI systems. Promoting efficient resource utilization contributes to more sustainable AI development. Our state-of-the-art proofs and principles demonstrate the framework's effectiveness in responsibly democratizing artificial intelligence, offering a promising approach for building secure and private foundational models.

Self-supervised learning (SSL) has gained significant interest in recent years as a solution to address the challenges posed by sparse and noisy data in recommender systems. Despite the growing number of SSL algorithms designed to provide state-of-the-art performance in various recommendation scenarios (e.g., graph collaborative filtering, sequential recommendation, social recommendation, KG-enhanced recommendation), there is still a lack of unified frameworks that integrate recommendation algorithms across different domains. Such a framework could serve as the cornerstone for self-supervised recommendation algorithms, unifying the validation of existing methods and driving the design of new ones. To address this gap, we introduce SSLRec, a novel benchmark platform that provides a standardized, flexible, and comprehensive framework for evaluating various SSL-enhanced recommenders. The SSLRec framework features a modular architecture that allows users to easily evaluate state-of-the-art models and a complete set of data augmentation and self-supervised toolkits to help create SSL recommendation models with specific needs. Furthermore, SSLRec simplifies the process of training and evaluating different recommendation models with consistent and fair settings. Our SSLRec platform covers a comprehensive set of state-of-the-art SSL-enhanced recommendation models across different scenarios, enabling researchers to evaluate these cutting-edge models and drive further innovation in the field. Our implemented SSLRec framework is available at the source code repository https://github.com/HKUDS/SSLRec.

Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particularly involving scientifically sophisticated risks, remains underexplored. Existing safety benchmarks typically focus either on instructions requiring minimal knowledge comprehension (e.g., ``tell me how to build a bomb") or utilize prompts that are relatively low-risk (e.g., multiple-choice or classification tasks about hazardous content). Consequently, they fail to adequately assess model safety when handling knowledge-intensive, hazardous scenarios. To address this critical gap, we introduce SOSBench, a regulation-grounded, hazard-focused benchmark encompassing six high-risk scientific domains: chemistry, biology, medicine, pharmacology, physics, and psychology. The benchmark comprises 3,000 prompts derived from real-world regulations and laws, systematically expanded via an LLM-assisted evolutionary pipeline that introduces diverse, realistic misuse scenarios (e.g., detailed explosive synthesis instructions involving advanced chemical formulas). We evaluate frontier models within a unified evaluation framework using our SOSBench. Despite their alignment claims, advanced models consistently disclose policy-violating content across all domains, demonstrating alarmingly high rates of harmful responses (e.g., 79.1% for Deepseek-R1 and 47.3% for GPT-4.1). These results highlight significant safety alignment deficiencies and underscore urgent concerns regarding the responsible deployment of powerful LLMs.

Academic and policy proposals on algorithmic accountability often seek to understand algorithmic systems in their socio-technical context, recognising that they are produced by 'many hands'. Increasingly, however, algorithmic systems are also produced, deployed, and used within a supply chain comprising multiple actors tied together by flows of data between them. In such cases, it is the working together of an algorithmic supply chain of different actors who contribute to the production, deployment, use, and functionality that drives systems and produces particular outcomes. We argue that algorithmic accountability discussions must consider supply chains and the difficult implications they raise for the governance and accountability of algorithmic systems. In doing so, we explore algorithmic supply chains, locating them in their broader technical and political economic context and identifying some key features that should be understood in future work on algorithmic governance and accountability (particularly regarding general purpose AI services). To highlight ways forward and areas warranting attention, we further discuss some implications raised by supply chains: challenges for allocating accountability stemming from distributed responsibility for systems between actors, limited visibility due to the accountability horizon, service models of use and liability, and cross-border supply chains and regulatory arbitrage

The rapidly evolving fields of Machine Learning (ML) and Artificial Intelligence have witnessed the emergence of platforms like Hugging Face (HF) as central hubs for model development and sharing. This experience report synthesizes insights from two comprehensive studies conducted on HF, focusing on carbon emissions and the evolutionary and maintenance aspects of ML models. Our objective is to provide a practical guide for future researchers embarking on mining software repository studies within the HF ecosystem to enhance the quality of these studies. We delve into the intricacies of the replication package used in our studies, highlighting the pivotal tools and methodologies that facilitated our analysis. Furthermore, we propose a nuanced stratified sampling strategy tailored for the diverse HF Hub dataset, ensuring a representative and comprehensive analytical approach. The report also introduces preliminary guidelines, transitioning from repository mining to cohort studies, to establish causality in repository mining studies, particularly within the ML model of HF context. This transition is inspired by existing frameworks and is adapted to suit the unique characteristics of the HF model ecosystem. Our report serves as a guiding framework for researchers, contributing to the responsible and sustainable advancement of ML, and fostering a deeper understanding of the broader implications of ML models.

Effectively leveraging private datasets remains a significant challenge in developing foundation models. Federated Learning (FL) has recently emerged as a collaborative framework that enables multiple users to fine-tune these models while mitigating data privacy risks. Meanwhile, Low-Rank Adaptation (LoRA) offers a resource-efficient alternative for fine-tuning foundation models by dramatically reducing the number of trainable parameters. This survey examines how LoRA has been integrated into federated fine-tuning for foundation models, an area we term FedLoRA, by focusing on three key challenges: distributed learning, heterogeneity, and efficiency. We further categorize existing work based on the specific methods used to address each challenge. Finally, we discuss open research questions and highlight promising directions for future investigation, outlining the next steps for advancing FedLoRA.

We present a privacy-preserving distributed learning framework for telecom ecosystems in the 6G-era that enables the vision of shared ownership and governance of ML models, while protecting the privacy of the data owners. We demonstrate its benefits by applying it to the use-case of Quality of Transmission (QoT) estimation in multi-domain multi-vendor optical networks, where no data of individual domains is shared with the network management system (NMS).

Recently, neural networks have been widely used in e-commerce recommender systems, owing to the rapid development of deep learning. We formalize the recommender system as a sequential recommendation problem, intending to predict the next items that the user might be interacted with. Recent works usually give an overall embedding from a user's behavior sequence. However, a unified user embedding cannot reflect the user's multiple interests during a period. In this paper, we propose a novel controllable multi-interest framework for the sequential recommendation, called ComiRec. Our multi-interest module captures multiple interests from user behavior sequences, which can be exploited for retrieving candidate items from the large-scale item pool. These items are then fed into an aggregation module to obtain the overall recommendation. The aggregation module leverages a controllable factor to balance the recommendation accuracy and diversity. We conduct experiments for the sequential recommendation on two real-world datasets, Amazon and Taobao. Experimental results demonstrate that our framework achieves significant improvements over state-of-the-art models. Our framework has also been successfully deployed on the offline Alibaba distributed cloud platform.

The financial domain poses unique challenges for knowledge graph (KG) construction at scale due to the complexity and regulatory nature of financial documents. Despite the critical importance of structured financial knowledge, the field lacks large-scale, open-source datasets capturing rich semantic relationships from corporate disclosures. We introduce an open-source, large-scale financial knowledge graph dataset built from the latest annual SEC 10-K filings of all S and P 100 companies - a comprehensive resource designed to catalyze research in financial AI. We propose a robust and generalizable knowledge graph (KG) construction framework that integrates intelligent document parsing, table-aware chunking, and schema-guided iterative extraction with a reflection-driven feedback loop. Our system incorporates a comprehensive evaluation pipeline, combining rule-based checks, statistical validation, and LLM-as-a-Judge assessments to holistically measure extraction quality. We support three extraction modes - single-pass, multi-pass, and reflection-agent-based - allowing flexible trade-offs between efficiency, accuracy, and reliability based on user requirements. Empirical evaluations demonstrate that the reflection-agent-based mode consistently achieves the best balance, attaining a 64.8 percent compliance score against all rule-based policies (CheckRules) and outperforming baseline methods (single-pass and multi-pass) across key metrics such as precision, comprehensiveness, and relevance in LLM-guided evaluations.

Automating legal document drafting can significantly enhance efficiency, reduce manual effort, and streamline legal workflows. While prior research has explored tasks such as judgment prediction and case summarization, the structured generation of private legal documents in the Indian legal domain remains largely unaddressed. To bridge this gap, we introduce VidhikDastaavej, a novel, anonymized dataset of private legal documents, and develop NyayaShilp, a fine-tuned legal document generation model specifically adapted to Indian legal texts. We propose a Model-Agnostic Wrapper (MAW), a two-step framework that first generates structured section titles and then iteratively produces content while leveraging retrieval-based mechanisms to ensure coherence and factual accuracy. We benchmark multiple open-source LLMs, including instruction-tuned and domain-adapted versions, alongside proprietary models for comparison. Our findings indicate that while direct fine-tuning on small datasets does not always yield improvements, our structured wrapper significantly enhances coherence, factual adherence, and overall document quality while mitigating hallucinations. To ensure real-world applicability, we developed a Human-in-the-Loop (HITL) Document Generation System, an interactive user interface that enables users to specify document types, refine section details, and generate structured legal drafts. This tool allows legal professionals and researchers to generate, validate, and refine AI-generated legal documents efficiently. Extensive evaluations, including expert assessments, confirm that our framework achieves high reliability in structured legal drafting. This research establishes a scalable and adaptable foundation for AI-assisted legal drafting in India, offering an effective approach to structured legal document generation.

Unfair treatment and discrimination are critical ethical concerns in AI systems, particularly as their adoption expands across diverse domains. Addressing these challenges, the recent introduction of the EU AI Act establishes a unified legal framework to ensure legal certainty for AI innovation and investment while safeguarding public interests, such as health, safety, fundamental rights, democracy, and the rule of law (Recital 8). The Act encourages stakeholders to initiate dialogue on existing AI fairness notions to address discriminatory outcomes of AI systems. However, these notions often overlook the critical role of Socio-Economic Status (SES), inadvertently perpetuating biases that favour the economically advantaged. This is concerning, given that principles of equalization advocate for equalizing resources or opportunities to mitigate disadvantages beyond an individual's control. While provisions for discrimination are laid down in the AI Act, specialized directions should be broadened, particularly in addressing economic disparities perpetuated by AI systems. In this work, we explore the limitations of popular AI fairness notions using a real-world dataset (Adult), highlighting their inability to address SES-driven disparities. To fill this gap, we propose a novel fairness notion, Socio-Economic Parity (SEP), which incorporates SES and promotes positive actions for underprivileged groups while accounting for factors within an individual's control, such as working hours, which can serve as a proxy for effort. We define a corresponding fairness measure and optimize a model constrained by SEP to demonstrate practical utility. Our results show the effectiveness of SEP in mitigating SES-driven biases. By analyzing the AI Act alongside our method, we lay a foundation for aligning AI fairness with SES factors while ensuring legal compliance.

Sustainability encompasses three key facets: economic, environmental, and social. However, the nascent discourse that is emerging on sustainable artificial intelligence (AI) has predominantly focused on the environmental sustainability of AI, often neglecting the economic and social aspects. Achieving truly sustainable AI necessitates addressing the tension between its climate awareness and its social sustainability, which hinges on equitable access to AI development resources. The concept of resource awareness advocates for broader access to the infrastructure required to develop AI, fostering equity in AI innovation. Yet, this push for improving accessibility often overlooks the environmental costs of expanding such resource usage. In this position paper, we argue that reconciling climate and resource awareness is essential to realizing the full potential of sustainable AI. We use the framework of base-superstructure to analyze how the material conditions are influencing the current AI discourse. We also introduce the Climate and Resource Aware Machine Learning (CARAML) framework to address this conflict and propose actionable recommendations spanning individual, community, industry, government, and global levels to achieve sustainable AI.

Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for what a model can do - its capabilities - without assessing what it would do if endowed with high-risk capabilities. This leaves a critical blind spot: models may strategically conceal capabilities or rapidly acquire them, while harboring latent inclinations toward misuse. We argue that propensity - the likelihood of a model to pursue harmful actions if empowered - is a critical, yet underexplored, axis of safety evaluation. We present PropensityBench, a novel benchmark framework that assesses the proclivity of models to engage in risky behaviors when equipped with simulated dangerous capabilities using proxy tools. Our framework includes 5,874 scenarios with 6,648 tools spanning four high-risk domains: cybersecurity, self-proliferation, biosecurity, and chemical security. We simulate access to powerful capabilities via a controlled agentic environment and evaluate the models' choices under varying operational pressures that reflect real-world constraints or incentives models may encounter, such as resource scarcity or gaining more autonomy. Across open-source and proprietary frontier models, we uncover 9 alarming signs of propensity: models frequently choose high-risk tools when under pressure, despite lacking the capability to execute such actions unaided. These findings call for a shift from static capability audits toward dynamic propensity assessments as a prerequisite for deploying frontier AI systems safely. Our code is available at https://github.com/scaleapi/propensity-evaluation.

The rapid integration of agentic AI into high-stakes real-world applications requires robust oversight mechanisms. The emerging field of AI Control (AIC) aims to provide such an oversight mechanism, but practical adoption depends heavily on implementation overhead. To study this problem better, we introduce the notion of Control tax -- the operational and financial cost of integrating control measures into AI pipelines. Our work makes three key contributions to the field of AIC: (1) we introduce a theoretical framework that quantifies the Control Tax and maps classifier performance to safety assurances; (2) we conduct comprehensive evaluations of state-of-the-art language models in adversarial settings, where attacker models insert subtle backdoors into code while monitoring models attempt to detect these vulnerabilities; and (3) we provide empirical financial cost estimates for control protocols and develop optimized monitoring strategies that balance safety and cost-effectiveness while accounting for practical constraints like auditing budgets. Our framework enables practitioners to make informed decisions by systematically connecting safety guarantees with their costs, advancing AIC through principled economic feasibility assessment across different deployment contexts.

The legality of training language models (LMs) on copyrighted or otherwise restricted data is under intense debate. However, as we show, model performance significantly degrades if trained only on low-risk text (e.g., out-of-copyright books or government documents), due to its limited size and domain coverage. We present SILO, a new language model that manages this risk-performance tradeoff during inference. SILO is built by (1) training a parametric LM on Open License Corpus (OLC), a new corpus we curate with 228B tokens of public domain and permissively licensed text and (2) augmenting it with a more general and easily modifiable nonparametric datastore (e.g., containing copyrighted books or news) that is only queried during inference. The datastore allows use of high-risk data without training on it, supports sentence-level data attribution, and enables data producers to opt out from the model by removing content from the store. These capabilities can foster compliance with data-use regulations such as the fair use doctrine in the United States and the GDPR in the European Union. Our experiments show that the parametric LM struggles on domains not covered by OLC. However, access to the datastore greatly improves out of domain performance, closing 90% of the performance gap with an LM trained on the Pile, a more diverse corpus with mostly high-risk text. We also analyze which nonparametric approach works best, where the remaining errors lie, and how performance scales with datastore size. Our results suggest that it is possible to build high quality language models while mitigating their legal risk.

Foundation model development attracts a rapidly expanding body of contributors, scientists, and applications. To help shape responsible development practices, we introduce the Foundation Model Development Cheatsheet: a growing collection of 250+ tools and resources spanning text, vision, and speech modalities. We draw on a large body of prior work to survey resources (e.g. software, documentation, frameworks, guides, and practical tools) that support informed data selection, processing, and understanding, precise and limitation-aware artifact documentation, efficient model training, advance awareness of the environmental impact from training, careful model evaluation of capabilities, risks, and claims, as well as responsible model release, licensing and deployment practices. We hope this curated collection of resources helps guide more responsible development. The process of curating this list, enabled us to review the AI development ecosystem, revealing what tools are critically missing, misused, or over-used in existing practices. We find that (i) tools for data sourcing, model evaluation, and monitoring are critically under-serving ethical and real-world needs, (ii) evaluations for model safety, capabilities, and environmental impact all lack reproducibility and transparency, (iii) text and particularly English-centric analyses continue to dominate over multilingual and multi-modal analyses, and (iv) evaluation of systems, rather than just models, is needed so that capabilities and impact are assessed in context.

Many individuals are concerned about the governance of machine learning systems and the prevention of algorithmic harms. The EU's recent General Data Protection Regulation (GDPR) has been seen as a core tool for achieving better governance of this area. While the GDPR does apply to the use of models in some limited situations, most of its provisions relate to the governance of personal data, while models have traditionally been seen as intellectual property. We present recent work from the information security literature around `model inversion' and `membership inference' attacks, which indicate that the process of turning training data into machine learned systems is not one-way, and demonstrate how this could lead some models to be legally classified as personal data. Taking this as a probing experiment, we explore the different rights and obligations this would trigger and their utility, and posit future directions for algorithmic governance and regulation.

We propose a framework for classifying the capabilities and behavior of Artificial General Intelligence (AGI) models and their precursors. This framework introduces levels of AGI performance, generality, and autonomy, providing a common language to compare models, assess risks, and measure progress along the path to AGI. To develop our framework, we analyze existing definitions of AGI, and distill six principles that a useful ontology for AGI should satisfy. With these principles in mind, we propose "Levels of AGI" based on depth (performance) and breadth (generality) of capabilities, and reflect on how current systems fit into this ontology. We discuss the challenging requirements for future benchmarks that quantify the behavior and capabilities of AGI models against these levels. Finally, we discuss how these levels of AGI interact with deployment considerations such as autonomy and risk, and emphasize the importance of carefully selecting Human-AI Interaction paradigms for responsible and safe deployment of highly capable AI systems.

Foundation models are powerful technologies: how they are released publicly directly shapes their societal impact. In this position paper, we focus on open foundation models, defined here as those with broadly available model weights (e.g. Llama 2, Stable Diffusion XL). We identify five distinctive properties (e.g. greater customizability, poor monitoring) of open foundation models that lead to both their benefits and risks. Open foundation models present significant benefits, with some caveats, that span innovation, competition, the distribution of decision-making power, and transparency. To understand their risks of misuse, we design a risk assessment framework for analyzing their marginal risk. Across several misuse vectors (e.g. cyberattacks, bioweapons), we find that current research is insufficient to effectively characterize the marginal risk of open foundation models relative to pre-existing technologies. The framework helps explain why the marginal risk is low in some cases, clarifies disagreements about misuse risks by revealing that past work has focused on different subsets of the framework with different assumptions, and articulates a way forward for more constructive debate. Overall, our work helps support a more grounded assessment of the societal impact of open foundation models by outlining what research is needed to empirically validate their theoretical benefits and risks.

Hidden license conflicts in the open-source AI ecosystem pose serious legal and ethical risks, exposing organizations to potential litigation and users to undisclosed risk. However, the field lacks a data-driven understanding of how frequently these conflicts occur, where they originate, and which communities are most affected. We present the first end-to-end audit of licenses for datasets and models on Hugging Face, as well as their downstream integration into open-source software applications, covering 364 thousand datasets, 1.6 million models, and 140 thousand GitHub projects. Our empirical analysis reveals systemic non-compliance in which 35.5% of model-to-application transitions eliminate restrictive license clauses by relicensing under permissive terms. In addition, we prototype an extensible rule engine that encodes almost 200 SPDX and model-specific clauses for detecting license conflicts, which can solve 86.4% of license conflicts in software applications. To support future research, we release our dataset and the prototype engine. Our study highlights license compliance as a critical governance challenge in open-source AI and provides both the data and tools necessary to enable automated, AI-aware compliance at scale.

Applications of Generative AI (Gen AI) are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for these seismic changes has triggered a lively debate about the potential risks of the technology, and resulted in calls for tighter regulation, in particular from some of the major tech companies who are leading in AI development. This regulation is likely to put at risk the budding field of open-source generative AI. Using a three-stage framework for Gen AI development (near, mid and long-term), we analyze the risks and opportunities of open-source generative AI models with similar capabilities to the ones currently available (near to mid-term) and with greater capabilities (long-term). We argue that, overall, the benefits of open-source Gen AI outweigh its risks. As such, we encourage the open sourcing of models, training and evaluation data, and provide a set of recommendations and best practices for managing risks associated with open-source generative AI.

The impressive performance of ChatGPT and other foundation-model-based products in human language understanding has prompted both academia and industry to explore how these models can be tailored for specific industries and application scenarios. This process, known as the customization of domain-specific foundation models (FMs), addresses the limitations of general-purpose models, which may not fully capture the unique patterns and requirements of domain-specific data. Despite its importance, there is a notable lack of comprehensive overview papers on building domain-specific FMs, while numerous resources exist for general-purpose models. To bridge this gap, this article provides a timely and thorough overview of the methodology for customizing domain-specific FMs. It introduces basic concepts, outlines the general architecture, and surveys key methods for constructing domain-specific models. Furthermore, the article discusses various domains that can benefit from these specialized models and highlights the challenges ahead. Through this overview, we aim to offer valuable guidance and reference for researchers and practitioners from diverse fields to develop their own customized FMs.

We study question answering in the domain of radio regulations, a legally sensitive and high-stakes area. We propose a telecom-specific Retrieval-Augmented Generation (RAG) pipeline and introduce, to our knowledge, the first multiple-choice evaluation set for this domain, constructed from authoritative sources using automated filtering and human validation. To assess retrieval quality, we define a domain-specific retrieval metric, under which our retriever achieves approximately 97% accuracy. Beyond retrieval, our approach consistently improves generation accuracy across all tested models. In particular, while naively inserting documents without structured retrieval yields only marginal gains for GPT-4o (less than 1%), applying our pipeline results in nearly a 12% relative improvement. These findings demonstrate that carefully targeted grounding provides a simple yet strong baseline and an effective domain-specific solution for regulatory question answering. All code and evaluation scripts, along with our derived question-answer dataset, are available at https://github.com/Zakaria010/Radio-RAG.

The evolution of machine learning has increasingly prioritized the development of powerful models and more scalable supervision signals. However, the emergence of foundation models presents significant challenges in providing effective supervision signals necessary for further enhancing their capabilities. Consequently, there is an urgent need to explore novel supervision signals and technical approaches. In this paper, we propose verifier engineering, a novel post-training paradigm specifically designed for the era of foundation models. The core of verifier engineering involves leveraging a suite of automated verifiers to perform verification tasks and deliver meaningful feedback to foundation models. We systematically categorize the verifier engineering process into three essential stages: search, verify, and feedback, and provide a comprehensive review of state-of-the-art research developments within each stage. We believe that verifier engineering constitutes a fundamental pathway toward achieving Artificial General Intelligence.

Instruction fine-tuning (IFT) elicits instruction following capabilities and steers the behavior of large language models (LLMs) via supervised learning. However, existing models trained on open-source IFT datasets only have the ability to follow instructions from users, and often fail to follow complex role and rules specified by developers, a.k.a. system prompts. The ability to follow these roles and rules is essential for deployment, as it ensures that the model safely interacts with users within developer defined guidelines. To improve such role and rule following ability, we propose \model, an automated data generation pipeline that generates diverse roles and rules from existing IFT instructions, along with corresponding responses. This data can then be used to train models that follow complex system prompts. The models are evaluated on our newly created benchmarks for role and rule following ability, as well as standard instruction-following benchmarks and general NLP tasks. Our framework significantly improves role and rule following capability in LLMs, as evidenced by over 25% increase in pass-rate on rule adherence, i.e. following all requirements, in our experiments with the Alpaca and Ultrachat datasets. Moreover, our models achieves this increase without any regression on popular instruction following benchmarks.

Large language models (LLMs), both proprietary and open-source, have demonstrated remarkable capabilities across various natural language processing tasks. However, they face significant limitations in legal reasoning tasks. Proprietary models introduce data privacy risks and high inference costs, while open-source models underperform due to insufficient legal domain training data. To address these limitations, we study data generation for legal reasoning to improve the legal reasoning performance of open-source LLMs with the help of proprietary LLMs. This is challenging due to the lack of legal knowledge in proprietary LLMs and the difficulty in verifying the generated data. We propose KgDG, a knowledge-guided data generation framework for legal reasoning. Our framework enables leveraging legal knowledge to enhance generation diversity and introduces a refinement and verification process to ensure the quality of generated data. Moreover, we expand the generated dataset to further enhance the LLM reasoning capabilities. Using KgDG, we create a synthetic legal reasoning dataset containing 50K high-quality examples. Our trained model LawGPT outperforms existing legal-specific LLMs and achieves performance comparable to proprietary LLMs, demonstrating the effectiveness of KgDG and LawGPT. Our code and resources is publicly available at https://anonymous.4open.science/r/KgDG-45F5 .

Supply chain operations traditionally involve a variety of complex decision making problems. Over the last few decades, supply chains greatly benefited from advances in computation, which allowed the transition from manual processing to automation and cost-effective optimization. Nonetheless, business operators still need to spend substantial efforts in explaining and interpreting the optimization outcomes to stakeholders. Motivated by the recent advances in Large Language Models (LLMs), we study how this disruptive technology can help bridge the gap between supply chain automation and human comprehension and trust thereof. We design -- a framework that accepts as input queries in plain text, and outputs insights about the underlying optimization outcomes. Our framework does not forgo the state-of-the-art combinatorial optimization technology, but rather leverages it to quantitatively answer what-if scenarios (e.g., how would the cost change if we used supplier B instead of supplier A for a given demand?). Importantly, our design does not require sending proprietary data over to LLMs, which can be a privacy concern in some circumstances. We demonstrate the effectiveness of our framework on a real server placement scenario within Microsoft's cloud supply chain. Along the way, we develop a general evaluation benchmark, which can be used to evaluate the accuracy of the LLM output in other scenarios.

Recently pre-trained Foundation Models (FMs) have been combined with Federated Learning (FL) to improve training of downstream tasks while preserving privacy. However, deploying FMs over edge networks with resource-constrained Internet of Things (IoT) devices is under-explored. This paper proposes a novel framework, namely, Federated Distilling knowledge to Prompt (FedD2P), for leveraging the robust representation abilities of a vision-language FM without deploying it locally on edge devices. This framework distills the aggregated knowledge of IoT devices to a prompt generator to efficiently adapt the frozen FM for downstream tasks. To eliminate the dependency on a public dataset, our framework leverages perclass local knowledge from IoT devices and linguistic descriptions of classes to train the prompt generator. Our experiments on diverse image classification datasets CIFAR, OxfordPets, SVHN, EuroSAT, and DTD show that FedD2P outperforms the baselines in terms of model performance.

Policy Compliance Detection (PCD) is a task we encounter when reasoning over texts, e.g. legal frameworks. Previous work to address PCD relies heavily on modeling the task as a special case of Recognizing Textual Entailment. Entailment is applicable to the problem of PCD, however viewing the policy as a single proposition, as opposed to multiple interlinked propositions, yields poor performance and lacks explainability. To address this challenge, more recent proposals for PCD have argued for decomposing policies into expression trees consisting of questions connected with logic operators. Question answering is used to obtain answers to these questions with respect to a scenario. Finally, the expression tree is evaluated in order to arrive at an overall solution. However, this work assumes expression trees are provided by experts, thus limiting its applicability to new policies. In this work, we learn how to infer expression trees automatically from policy texts. We ensure the validity of the inferred trees by introducing constrained decoding using a finite state automaton to ensure the generation of valid trees. We determine through automatic evaluation that 63% of the expression trees generated by our constrained generation model are logically equivalent to gold trees. Human evaluation shows that 88% of trees generated by our model are correct.

Anti-money laundering (AML) regulations play a critical role in safeguarding financial systems, but bear high costs for institutions and drive financial exclusion for those on the socioeconomic and international margins. The advent of cryptocurrency has introduced an intriguing paradox: pseudonymity allows criminals to hide in plain sight, but open data gives more power to investigators and enables the crowdsourcing of forensic analysis. Meanwhile advances in learning algorithms show great promise for the AML toolkit. In this workshop tutorial, we motivate the opportunity to reconcile the cause of safety with that of financial inclusion. We contribute the Elliptic Data Set, a time series graph of over 200K Bitcoin transactions (nodes), 234K directed payment flows (edges), and 166 node features, including ones based on non-public data; to our knowledge, this is the largest labelled transaction data set publicly available in any cryptocurrency. We share results from a binary classification task predicting illicit transactions using variations of Logistic Regression (LR), Random Forest (RF), Multilayer Perceptrons (MLP), and Graph Convolutional Networks (GCN), with GCN being of special interest as an emergent new method for capturing relational information. The results show the superiority of Random Forest (RF), but also invite algorithmic work to combine the respective powers of RF and graph methods. Lastly, we consider visualization for analysis and explainability, which is difficult given the size and dynamism of real-world transaction graphs, and we offer a simple prototype capable of navigating the graph and observing model performance on illicit activity over time. With this tutorial and data set, we hope to a) invite feedback in support of our ongoing inquiry, and b) inspire others to work on this societally important challenge.

The field of explainable AI (XAI) has quickly become a thriving and prolific community. However, a silent, recurrent and acknowledged issue in this area is the lack of consensus regarding its terminology. In particular, each new contribution seems to rely on its own (and often intuitive) version of terms like "explanation" and "interpretation". Such disarray encumbers the consolidation of advances in the field towards the fulfillment of scientific and regulatory demands e.g., when comparing methods or establishing their compliance with respect to biases and fairness constraints. We propose a theoretical framework that not only provides concrete definitions for these terms, but it also outlines all steps necessary to produce explanations and interpretations. The framework also allows for existing contributions to be re-contextualized such that their scope can be measured, thus making them comparable to other methods. We show that this framework is compliant with desiderata on explanations, on interpretability and on evaluation metrics. We present a use-case showing how the framework can be used to compare LIME, SHAP and MDNet, establishing their advantages and shortcomings. Finally, we discuss relevant trends in XAI as well as recommendations for future work, all from the standpoint of our framework.

Tabular foundation models represent a growing paradigm in structured data learning, extending the benefits of large-scale pretraining to tabular domains. However, their adoption remains limited due to heterogeneous preprocessing pipelines, fragmented APIs, inconsistent fine-tuning procedures, and the absence of standardized evaluation for deployment-oriented metrics such as calibration and fairness. We present TabTune, a unified library that standardizes the complete workflow for tabular foundation models through a single interface. TabTune provides consistent access to seven state-of-the-art models supporting multiple adaptation strategies, including zero-shot inference, meta-learning, supervised fine-tuning (SFT), and parameter-efficient fine-tuning (PEFT). The framework automates model-aware preprocessing, manages architectural heterogeneity internally, and integrates evaluation modules for performance, calibration, and fairness. Designed for extensibility and reproducibility, TabTune enables consistent benchmarking of adaptation strategies of tabular foundation models. The library is open source and available at https://github.com/Lexsi-Labs/TabTune .

This paper proposes a novel framework to predict traffic flows' bandwidth ahead of time. Modern network management systems share a common issue: the network situation evolves between the moment the decision is made and the moment when actions (countermeasures) are applied. This framework converts packets from real-life traffic into flows containing relevant features. Machine learning models, including Decision Tree, Random Forest, XGBoost, and Deep Neural Network, are trained on these data to predict the bandwidth at the next time instance for every flow. Predictions can be fed to the management system instead of current flows bandwidth in order to take decisions on a more accurate network state. Experiments were performed on 981,774 flows and 15 different time windows (from 0.03s to 4s). They show that the Random Forest is the best performing and most reliable model, with a predictive performance consistently better than relying on the current bandwidth (+19.73% in mean absolute error and +18.00% in root mean square error). Experimental results indicate that this framework can help network management systems to take more informed decisions using a predicted network state.

Personalized financial advice requires consideration of user goals, constraints, risk tolerance, and jurisdiction. Prior LLM work has focused on support systems for investors and financial planners. Simultaneously, numerous recent studies examine broader personal finance tasks, including budgeting, debt management, retirement, and estate planning, through agentic pipelines that incur high maintenance costs, yielding less than 25% of their expected financial returns. In this study, we introduce a novel and reproducible framework that integrates relevant financial context with behavioral finance studies to construct supervision data for end-to-end advisors. Using this framework, we create a 19k sample reasoning dataset and conduct a comprehensive fine-tuning of the Qwen-3-8B model on the dataset. Through a held-out test split and a blind LLM-jury study, we demonstrate that through careful data curation and behavioral integration, our 8B model achieves performance comparable to significantly larger baselines (14-32B parameters) across factual accuracy, fluency, and personalization metrics while incurring 80% lower costs than the larger counterparts.

The rapid rise of open-weight and open-source foundation models is intensifying the obligation and reshaping the opportunity to make AI systems safe. This paper reports outcomes from the Columbia Convening on AI Openness and Safety (San Francisco, 19 Nov 2024) and its six-week preparatory programme involving more than forty-five researchers, engineers, and policy leaders from academia, industry, civil society, and government. Using a participatory, solutions-oriented process, the working groups produced (i) a research agenda at the intersection of safety and open source AI; (ii) a mapping of existing and needed technical interventions and open source tools to safely and responsibly deploy open foundation models across the AI development workflow; and (iii) a mapping of the content safety filter ecosystem with a proposed roadmap for future research and development. We find that openness -- understood as transparent weights, interoperable tooling, and public governance -- can enhance safety by enabling independent scrutiny, decentralized mitigation, and culturally plural oversight. However, significant gaps persist: scarce multimodal and multilingual benchmarks, limited defenses against prompt-injection and compositional attacks in agentic systems, and insufficient participatory mechanisms for communities most affected by AI harms. The paper concludes with a roadmap of five priority research directions, emphasizing participatory inputs, future-proof content filters, ecosystem-wide safety infrastructure, rigorous agentic safeguards, and expanded harm taxonomies. These recommendations informed the February 2025 French AI Action Summit and lay groundwork for an open, plural, and accountable AI safety discipline.

The emergent phenomena of large foundation models have revolutionized natural language processing. However, evaluating these models presents significant challenges due to their size, capabilities, and deployment across diverse applications. Existing literature often focuses on individual aspects, such as benchmark performance or specific tasks, but fails to provide a cohesive process that integrates the nuances of diverse use cases with broader ethical and operational considerations. This work focuses on three key aspects: (1) Formalizing the Evaluation Process by providing a structured framework tailored to specific use-case contexts, (2) Offering Actionable Tools and Frameworks such as checklists and templates to ensure thorough, reproducible, and practical evaluations, and (3) Surveying Recent Work with a targeted review of advancements in LLM evaluation, emphasizing real-world applications.

In recent years, Large Language Models (LLM) such as ChatGPT, CoPilot, and Gemini have been widely adopted in different areas. As the use of LLMs continues to grow, many efforts have focused on reducing the massive training overheads of these models. But it is the environmental impact of handling user requests to LLMs that is increasingly becoming a concern. Recent studies estimate that the costs of operating LLMs in their inference phase can exceed training costs by 25x per year. As LLMs are queried incessantly, the cumulative carbon footprint for the operational phase has been shown to far exceed the footprint during the training phase. Further, estimates indicate that 500 ml of fresh water is expended for every 20-50 requests to LLMs during inference. To address these important sustainability issues with LLMs, we propose a novel framework called SLIT to co-optimize LLM quality of service (time-to-first token), carbon emissions, water usage, and energy costs. The framework utilizes a machine learning (ML) based metaheuristic to enhance the sustainability of LLM hosting across geo-distributed cloud datacenters. Such a framework will become increasingly vital as LLMs proliferate.

Foundation models for single-cell RNA sequencing (scRNA-seq) have shown promising capabilities in capturing gene expression patterns. However, current approaches face critical limitations: they ignore biological prior knowledge encoded in gene regulatory relationships and fail to leverage multi-omics signals that could provide complementary regulatory insights. In this paper, we propose GRNFormer, a new framework that systematically integrates multi-scale Gene Regulatory Networks (GRNs) inferred from multi-omics data into RNA foundation model training. Our framework introduces two key innovations. First, we introduce a pipeline for constructing hierarchical GRNs that capture regulatory relationships at both cell-type-specific and cell-specific resolutions. Second, we design a structure-aware integration framework that addresses the information asymmetry in GRNs through two technical advances: (1) A graph topological adapter using multi-head cross-attention to weight regulatory relationships dynamically, and (2) a novel edge perturbation strategy that perturb GRNs with biologically-informed co-expression links to augment graph neural network training. Comprehensive experiments have been conducted on three representative downstream tasks across multiple model architectures to demonstrate the effectiveness of GRNFormer. It achieves consistent improvements over state-of-the-art (SoTA) baselines: 3.6% increase in drug response prediction correlation, 9.6% improvement in single-cell drug classification AUC, and 1.1% average gain in gene perturbation prediction accuracy.

Enterprise Resource Planning (ERP) systems serve as the digital backbone of modern financial institutions, yet they continue to rely on static, rule-based workflows that limit adaptability, scalability, and intelligence. As business operations grow more complex and data-rich, conventional ERP platforms struggle to integrate structured and unstructured data in real time and to accommodate dynamic, cross-functional workflows. In this paper, we present the first AI-native, agent-based framework for ERP systems, introducing a novel architecture of Generative Business Process AI Agents (GBPAs) that bring autonomy, reasoning, and dynamic optimization to enterprise workflows. The proposed system integrates generative AI with business process modeling and multi-agent orchestration, enabling end-to-end automation of complex tasks such as budget planning, financial reporting, and wire transfer processing. Unlike traditional workflow engines, GBPAs interpret user intent, synthesize workflows in real time, and coordinate specialized sub-agents for modular task execution. We validate the framework through case studies in bank wire transfers and employee reimbursements, two representative financial workflows with distinct complexity and data modalities. Results show that GBPAs achieve up to 40% reduction in processing time, 94% drop in error rate, and improved regulatory compliance by enabling parallelism, risk control insertion, and semantic reasoning. These findings highlight the potential of GBPAs to bridge the gap between generative AI capabilities and enterprise-grade automation, laying the groundwork for the next generation of intelligent ERP systems.

Statutory article retrieval is the task of automatically retrieving law articles relevant to a legal question. While recent advances in natural language processing have sparked considerable interest in many legal tasks, statutory article retrieval remains primarily untouched due to the scarcity of large-scale and high-quality annotated datasets. To address this bottleneck, we introduce the Belgian Statutory Article Retrieval Dataset (BSARD), which consists of 1,100+ French native legal questions labeled by experienced jurists with relevant articles from a corpus of 22,600+ Belgian law articles. Using BSARD, we benchmark several state-of-the-art retrieval approaches, including lexical and dense architectures, both in zero-shot and supervised setups. We find that fine-tuned dense retrieval models significantly outperform other systems. Our best performing baseline achieves 74.8% R@100, which is promising for the feasibility of the task and indicates there is still room for improvement. By the specificity of the domain and addressed task, BSARD presents a unique challenge problem for future research on legal information retrieval. Our dataset and source code are publicly available.