{"total":182,"rows":[{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509,"area":"safety"},{"id":"2410.09024","title":"AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents","created":"2024-10-11","cited_by_count":437,"area":"agents"},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222,"area":null},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177,"area":null},{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2309.07124","title":"RAIN: Your Language Models Can Align Themselves without Finetuning","created":"2023-09-13","cited_by_count":157,"area":"alignment"},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148,"area":"alignment"},{"id":"2311.07590","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","created":"2023-11-09","cited_by_count":146,"area":null},{"id":"2404.16698","title":"Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents","created":"2024-04-25","cited_by_count":125,"area":"wm"},{"id":"2402.12348","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","created":"2024-02-19","cited_by_count":120,"area":"lr"},{"id":"2411.12990","title":"BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices","created":"2024-11-20","cited_by_count":114,"area":null},{"id":"2502.05589","title":"On Memory Construction and Retrieval for Personalized Conversational Agents","created":"2025-02-08","cited_by_count":105,"area":"rag"},{"id":"2310.01320","title":"Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation","created":"2023-10-02","cited_by_count":104,"area":"lr"},{"id":"2307.16513","title":"Deception Abilities Emerged in Large Language Models","created":"2023-07-31","cited_by_count":101,"area":null},{"id":"2404.10271","title":"Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback","created":"2024-04-16","cited_by_count":100,"area":"alignment"},{"id":"2307.03718","title":"Frontier AI Regulation: Managing Emerging Risks to Public Safety","created":"2023-07-06","cited_by_count":98,"area":null},{"id":"2308.08239","title":"MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation","created":"2023-08-16","cited_by_count":97,"area":null},{"id":"2309.15840","title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","created":"2023-09-26","cited_by_count":83,"area":null},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79,"area":null},{"id":"2307.00855","title":"Review of Large Vision Models and Visual Prompt Engineering","created":"2023-07-03","cited_by_count":77,"area":null},{"id":"2402.06627","title":"Feedback Loops With Language Models Drive In-Context Reward Hacking","created":"2024-02-09","cited_by_count":77,"area":"alignment"},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"area":"agents"},{"id":"2502.08640","title":"Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs","created":"2025-02-12","cited_by_count":67,"area":"agents"},{"id":"2308.15022","title":"Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models","created":"2023-08-29","cited_by_count":62,"area":null},{"id":"2305.13660","title":"Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning","created":"2023-05-23","cited_by_count":61,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2410.02683","title":"DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life","created":"2024-10-03","cited_by_count":59,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2306.09983","title":"Evaluating Superhuman Models with Consistency Checks","created":"2023-06-16","cited_by_count":47,"area":null},{"id":"2308.01404","title":"Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models","created":"2023-07-05","cited_by_count":47,"area":null},{"id":"2311.10538","title":"Testing Language Model Agents Safely in the Wild","created":"2023-11-17","cited_by_count":46,"area":"agents"},{"id":"2310.19677","title":"MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks","created":"2023-10-30","cited_by_count":44,"area":"alignment"},{"id":"2405.01576","title":"Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant","created":"2024-04-25","cited_by_count":38,"area":null},{"id":"2308.15399","title":"Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?","created":"2023-08-29","cited_by_count":36,"area":"lr"},{"id":"2401.01312","title":"LLM Harmony: Multi-Agent Communication for Problem Solving","created":"2024-01-02","cited_by_count":35,"area":"agents"},{"id":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32,"area":null},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32,"area":null},{"id":"2406.10957","title":"Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence","created":"2024-06-16","cited_by_count":31,"area":"alignment"},{"id":"2503.10728","title":"DarkBench: Benchmarking Dark Patterns in Large Language Models","created":"2025-03-13","cited_by_count":28,"area":null},{"id":"2501.16173","title":"Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma","created":"2025-01-27","cited_by_count":25,"area":"agents"},{"id":"2312.04021","title":"A Study on the Calibration of In-context Learning","created":"2023-12-07","cited_by_count":22,"area":null},{"id":"2502.07663","title":"Human Decision-making is Susceptible to AI-driven Manipulation","created":"2025-02-11","cited_by_count":19,"area":null},{"id":"2403.18152","title":"Large Language Models as Financial Data Annotators: A Study on Effectiveness and Efficiency","created":"2024-03-26","cited_by_count":18,"area":null},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2409.09467","title":"Keeping Humans in the Loop: Human-Centered Automated Annotation with Generative AI","created":"2024-09-14","cited_by_count":17,"area":null},{"id":"2502.08301","title":"Compromising Honesty and Harmlessness in Language Models via Deception Attacks","created":"2025-02-12","cited_by_count":17,"area":null},{"id":"2501.16513","title":"Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models","created":"2025-01-27","cited_by_count":16,"area":"lr"},{"id":"2310.15431","title":"What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations","created":"2023-10-24","cited_by_count":15,"area":null},{"id":"2412.17128","title":"Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models","created":"2024-12-22","cited_by_count":15,"area":null},{"id":"2505.19212","title":"When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas","created":"2025-05-25","cited_by_count":15,"area":null},{"id":"2508.06249","title":"In-Training Defenses against Emergent Misalignment in Language Models","created":"2025-08-08","cited_by_count":15,"area":"alignment"},{"id":"2604.17596","title":"Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories","created":"2026-04-19","cited_by_count":15,"area":null},{"id":"2307.10569","title":"Deceptive Alignment Monitoring","created":"2023-07-20","cited_by_count":14,"area":null},{"id":"2406.01364","title":"BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards","created":"2024-06-03","cited_by_count":14,"area":null},{"id":"2406.06435","title":"Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domain","created":"2024-06-10","cited_by_count":14,"area":null},{"id":"2310.17639","title":"In-Context Learning Dynamics with Random Binary Sequences","created":"2023-10-26","cited_by_count":13,"area":null},{"id":"2512.20798","title":"A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents","created":"2025-12-23","cited_by_count":13,"area":"agents"},{"id":"2410.09114","title":"Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities","created":"2024-10-10","cited_by_count":12,"area":"agents"},{"id":"2310.16763","title":"SuperHF: Supervised Iterative Learning from Human Feedback","created":"2023-10-25","cited_by_count":10,"area":"alignment"},{"id":"2405.04325","title":"Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation","created":"2024-05-07","cited_by_count":10,"area":null},{"id":"2411.11731","title":"Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment","created":"2024-11-18","cited_by_count":10,"area":null},{"id":"2503.18825","title":"EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agents","created":"2025-03-24","cited_by_count":10,"area":"agents"},{"id":"2510.14318","title":"Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL","created":"2025-10-16","cited_by_count":10,"area":null},{"id":"2603.07368","title":"Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness","created":"2026-03-07","cited_by_count":10,"area":null},{"id":"2406.20087","title":"ProgressGym: Alignment with a Millennium of Moral Progress","created":"2024-06-28","cited_by_count":9,"area":null},{"id":"2505.17441","title":"Discovering Forbidden Topics in Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2307.00787","title":"Evaluating Shutdown Avoidance of Language Models in Textual Scenarios","created":"2023-07-03","cited_by_count":8,"area":null},{"id":"2402.09404","title":"AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability","created":"2024-02-14","cited_by_count":8,"area":"lr"},{"id":"2405.12933","title":"Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs","created":"2024-05-21","cited_by_count":8,"area":"lr"},{"id":"2409.20303","title":"A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2601.08462","title":"M3-BENCH: Process-Aware Evaluation of LLM Agents' Social Behaviors in Mixed-Motive Games","created":"2026-01-13","cited_by_count":8,"area":"agents"},{"id":"2602.16662","title":"Evaluating Collective Behaviour of Hundreds of LLM Agents","created":"2026-02-18","cited_by_count":8,"area":"agents"},{"id":"2602.20273","title":"The Truthfulness Spectrum Hypothesis","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2609.29429","title":"Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures","created":"2026-09-24","cited_by_count":8,"area":"safety"},{"id":"2309.06364","title":"Framework-Based Qualitative Analysis of Free Responses of Large Language Models: Algorithmic Fidelity","created":"2023-09-06","cited_by_count":7,"area":null},{"id":"2312.01818","title":"Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto","created":"2023-12-04","cited_by_count":7,"area":"agents"},{"id":"2407.19760","title":"Legal Minds, Algorithmic Decisions: How LLMs Apply Constitutional Principles in Complex Scenarios","created":"2024-07-29","cited_by_count":7,"area":null},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2402.11811","title":"FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema","created":"2024-02-19","cited_by_count":6,"area":null},{"id":"2410.19720","title":"2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision","created":"2024-10-25","cited_by_count":6,"area":"alignment"},{"id":"2503.14427","title":"VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2510.00857","title":"ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2602.18182","title":"Capabilities Ain't All You Need: Measuring Propensities in AI","created":"2026-02-20","cited_by_count":6,"area":null},{"id":"2603.25326","title":"Evaluating Language Models for Harmful Manipulation","created":"2026-03-26","cited_by_count":6,"area":null},{"id":"2405.12999","title":"An Assessment of Model-On-Model Deception","created":"2024-05-10","cited_by_count":5,"area":null},{"id":"2411.11853","title":"Chat Bankman-Fried: an Exploration of LLM Alignment in Finance","created":"2024-11-01","cited_by_count":5,"area":"alignment"},{"id":"2603.06874","title":"LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models","created":"2026-03-06","cited_by_count":5,"area":"agents"},{"id":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2608.28945","title":"Automated Researchers Can Mitigate Well-characterized Alignment Failures","created":"2026-08-28","cited_by_count":5,"area":null},{"id":"2305.08290","title":"SWAN: A Generic Framework for Auditing Textual Conversational Systems","created":"2023-05-15","cited_by_count":4,"area":null},{"id":"2404.18978","title":"Towards Generalizable Agents in Text-Based Educational Environments: A Study of Integrating RL with LLMs","created":"2024-04-29","cited_by_count":4,"area":"agents"},{"id":"2410.12621","title":"Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning","created":"2024-10-16","cited_by_count":4,"area":"lr"},{"id":"2511.08565","title":"Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models","created":"2025-11-11","cited_by_count":4,"area":null},{"id":"2512.07667","title":"Depth-Wise Activation Steering for Honest Language Models","created":"2025-12-08","cited_by_count":4,"area":"mechinterp"},{"id":"2605.16282","title":"Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents","created":"2026-04-11","cited_by_count":4,"area":"agents"},{"id":"2605.27593","title":"Voluntary Collusion with Secret Tools in Competing LLM Agents","created":"2026-05-26","cited_by_count":4,"area":"agents"}],"next_cursor":"100"}