{"total":126,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257,"area":"lr"},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195,"area":"safety"},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151,"area":"safety"},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60,"area":null},{"id":"2410.03768","title":"Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs","created":"2024-10-02","cited_by_count":55,"area":null},{"id":"2402.00786","title":"CroissantLLM: A Truly Bilingual French-English Language Model","created":"2024-02-01","cited_by_count":53,"area":null},{"id":"2403.04893","title":"A Safe Harbor for AI Evaluation and Red Teaming","created":"2024-03-07","cited_by_count":47,"area":"safety"},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46,"area":null},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2407.14561","title":"NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals","created":"2024-07-18","cited_by_count":45,"area":null},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2503.10728","title":"DarkBench: Benchmarking Dark Patterns in Large Language Models","created":"2025-03-13","cited_by_count":28,"area":null},{"id":"2406.11852","title":"Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation","created":"2024-04-02","cited_by_count":27,"area":null},{"id":"2502.05489","title":"Mechanistic Interpretability of Emotion Inference in Large Language Models","created":"2025-02-08","cited_by_count":27,"area":"mechinterp"},{"id":"2406.13663","title":"Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation","created":"2024-06-19","cited_by_count":25,"area":"rag"},{"id":"2505.17120","title":"Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions","created":"2025-05-21","cited_by_count":25,"area":null},{"id":"2601.22594","title":"Language Model Circuits Are Sparse in the Neuron Basis","created":"2026-01-30","cited_by_count":25,"area":"mechinterp"},{"id":"2410.04772","title":"From Transparency to Accountability and Back: A Discussion of Access and Evidence in AI Auditing","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2410.16618","title":"SoK: Dataset Copyright Auditing in Machine Learning Systems","created":"2024-10-22","cited_by_count":15,"area":null},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2405.10799","title":"Training Compute Thresholds: Features and Functions in AI Regulation","created":"2024-05-17","cited_by_count":14,"area":null},{"id":"2402.12572","title":"FairProof : Confidential and Certifiable Fairness for Neural Networks","created":"2024-02-19","cited_by_count":13,"area":null},{"id":"2404.17047","title":"Near to Mid-term Risks and Opportunities of Open-Source Generative AI","created":"2024-04-25","cited_by_count":13,"area":null},{"id":"2405.05466","title":"Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals","created":"2024-05-08","cited_by_count":13,"area":null},{"id":"2405.08597","title":"Risks and Opportunities of Open-Source Generative AI","created":"2024-05-14","cited_by_count":13,"area":null},{"id":"2406.11757","title":"STAR: SocioTechnical Approach to Red Teaming Language Models","created":"2024-06-17","cited_by_count":13,"area":"safety"},{"id":"2503.01623","title":"Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2507.21928","title":"Vibe Coding as a Reconfiguration of Intent Mediation in Software Development: Definition, Implications, and Research Agenda","created":"2025-07-29","cited_by_count":13,"area":null},{"id":"2406.01352","title":"Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2412.11995","title":"Combining Large Language Models with Tutoring System Intelligence: A Case Study in Caregiver Homework Support","created":"2024-12-16","cited_by_count":11,"area":null},{"id":"2502.15620","title":"Paradigms of AI Evaluation: Mapping Goals, Methodologies and Culture","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2404.02675","title":"Responsible Reporting for Frontier AI Development","created":"2024-04-03","cited_by_count":10,"area":null},{"id":"2404.06737","title":"Disguised Copyright Infringement of Latent Diffusion Models","created":"2024-04-10","cited_by_count":10,"area":"diffusion"},{"id":"2406.11544","title":"Do Parameters Reveal More than Loss for Membership Inference?","created":"2024-06-17","cited_by_count":10,"area":"safety"},{"id":"2408.16074","title":"Verification methods for international AI agreements","created":"2024-08-28","cited_by_count":10,"area":null},{"id":"2411.19876","title":"LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states","created":"2024-11-29","cited_by_count":10,"area":"safety"},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2505.17441","title":"Discovering Forbidden Topics in Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2506.23706","title":"Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments","created":"2025-06-30","cited_by_count":8,"area":null},{"id":"2510.16171","title":"Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2604.09839","title":"Steered LLM Activations are Non-Surjective","created":"2026-04-10","cited_by_count":8,"area":"mechinterp"},{"id":"2403.07904","title":"Addressing the regulatory gap: moving towards an EU AI audit ecosystem beyond the AI Act by including civil society","created":"2024-02-26","cited_by_count":7,"area":null},{"id":"2410.02777","title":"Secure and Confidential Certificates of Online Fairness","created":"2024-09-17","cited_by_count":7,"area":null},{"id":"2505.11577","title":"The Accountability Paradox: How Platform API Restrictions Undermine AI Transparency Mandates","created":"2025-05-16","cited_by_count":7,"area":null},{"id":"2405.01531","title":"Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models","created":"2024-05-02","cited_by_count":6,"area":null},{"id":"2501.02997","title":"CALM: Curiosity-Driven Auditing for Large Language Models","created":"2025-01-06","cited_by_count":6,"area":null},{"id":"2510.21293","title":"Understanding AI Trustworthiness: A Scoping Review of AIES & FAccT Articles","created":"2025-10-24","cited_by_count":6,"area":null},{"id":"2606.05391","title":"Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"id":"2410.12104","title":"To Err is AI : A Case Study Informing LLM Flaw Reporting Practices","created":"2024-10-15","cited_by_count":5,"area":null},{"id":"2602.16201","title":"Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications","created":"2026-02-18","cited_by_count":5,"area":null},{"id":"2604.15559","title":"Subliminal Transfer of Unsafe Behaviors in AI Agent Distillation","created":"2026-04-16","cited_by_count":5,"area":"agents"},{"id":"2406.02619","title":"Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits","created":"2024-06-03","cited_by_count":4,"area":"safety"},{"id":"2411.12820","title":"Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation","created":"2024-11-19","cited_by_count":4,"area":null},{"id":"2412.08653","title":"What AI evaluations for preventing catastrophic risks can and cannot do","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2503.01470","title":"Position: Ensuring mutual privacy is necessary for effective external evaluation of proprietary AI systems","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2503.18956","title":"International Agreements on AI Safety: Review and Recommendations for a Conditional AI Safety Treaty","created":"2025-03-18","cited_by_count":4,"area":null},{"id":"2505.21800","title":"From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.03755","title":"Misalignment or misuse? The AGI alignment tradeoff","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2606.09809","title":"Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2406.14154","title":"Watching the Watchers: A Comparative Fairness Audit of Cloud-based Content Moderation Services","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2410.01064","title":"Truth or Deceit? A Bayesian Decoding Game Enhances Consistency and Reliability","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2411.04994","title":"Legacy Procurement Practices Shape How U.S. Cities Govern AI: Understanding Government Employees' Practices, Challenges, and Needs","created":"2024-11-07","cited_by_count":3,"area":null},{"id":"2503.17388","title":"AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2505.17760","title":"But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors","created":"2025-05-23","cited_by_count":3,"area":"mechinterp"},{"id":"2605.16198","title":"Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems","created":"2026-05-15","cited_by_count":3,"area":null},{"id":"2409.13708","title":"Towards Safe Multilingual Frontier AI","created":"2024-09-06","cited_by_count":2,"area":"safety"},{"id":"2412.12169","title":"Regulation of Language Models With Interpretability Will Likely Result In A Performance Trade-Off","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2504.00874","title":"P2NIA: Privacy-Preserving Non-Iterative Auditing","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2505.00802","title":"Explanations as Bias Detectors: A Critical Study of Local Post-hoc XAI Methods for Fairness Exploration","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2507.09801","title":"Technical Requirements for Halting Dangerous AI Activities","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2508.06755","title":"Many-Turn Jailbreaking","created":"2025-08-09","cited_by_count":2,"area":"safety"},{"id":"2509.05627","title":"Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternatives","created":"2025-09-06","cited_by_count":2,"area":null},{"id":"2511.12439","title":"Multi-agent Self-triage System with Medical Flowcharts","created":"2025-11-16","cited_by_count":2,"area":"agents"},{"id":"2602.06911","title":"TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering","created":"2026-02-06","cited_by_count":2,"area":"safety"},{"id":"2602.19844","title":"LLM-enabled Applications Require System-Level Threat Monitoring","created":"2026-02-23","cited_by_count":2,"area":null},{"id":"2605.15164","title":"Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2606.08044","title":"When Behavioral Safety Evaluation Fails: A Representation-Level Perspective","created":"2026-06-06","cited_by_count":2,"area":"safety"},{"id":"2404.08221","title":"Uncertain Boundaries: Multidisciplinary Approaches to Copyright Issues in Generative AI","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2502.11273","title":"FairFare: A Tool for Crowdsourcing Rideshare Data to Empower Labor Organizers","created":"2025-02-16","cited_by_count":1,"area":null},{"id":"2505.10719","title":"Tracr-Injection: Distilling Algorithms into Pre-trained Language Models","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2506.07691","title":"Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models","created":"2025-06-09","cited_by_count":1,"area":"mechinterp"},{"id":"2510.20612","title":"Black Box Absorption: LLMs Undermining Innovative Ideas","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2602.07259","title":"Incentive-Aware AI Safety via Strategic Resource Allocation: A Stackelberg Security Games Perspective","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2604.19001","title":"HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2605.06846","title":"Narrow Secret Loyalty Dodges Black-Box Audits","created":"2026-05-07","cited_by_count":1,"area":"safety"},{"id":"2606.04193","title":"Notarized Agents: Receiver-Attested Confidential Receipts for AI Agent Actions","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2607.08173","title":"Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets","created":"2026-07-09","cited_by_count":1,"area":"lr"},{"id":"2403.18537","title":"A Path Towards Legal Autonomy: An interoperable and explainable approach to extracting, transforming, loading and computing legal information using large language models, expert systems and Bayesian networks","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2503.20800","title":"Evidencing Unauthorized Training Data from AI Generated Content using Information Isotopes","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2506.15735","title":"ContextBench: Modifying Contexts for Targeted Latent Activation","created":"2025-06-15","cited_by_count":0,"area":null},{"id":"2506.18213","title":"A Conceptual Framework for AI Capability Evaluations","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2508.06592","title":"Towards Integrated Alignment","created":"2025-08-08","cited_by_count":0,"area":"alignment"},{"id":"2512.15469","title":"Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2601.03424","title":"Spectral Archaeology: The Causal Topology of Model Evolution","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.10102","title":"When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems","created":"2026-01-15","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}