{"total":1040,"rows":[{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879,"area":null},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261,"area":"alignment"},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204,"area":"synth"},{"id":"2405.20362","title":"Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools","created":"2024-05-30","cited_by_count":176,"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":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171,"area":"alignment"},{"id":"2410.12877","title":"Improving Instruction-Following in Language Models through Activation Steering","created":"2024-10-15","cited_by_count":160,"area":"mechinterp"},{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159,"area":"lr"},{"id":"2401.01301","title":"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models","created":"2024-01-02","cited_by_count":150,"area":null},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2311.03287","title":"Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges","created":"2023-11-06","cited_by_count":131,"area":"mllm"},{"id":"2505.13995","title":"ELEPHANT: Measuring and understanding social sycophancy in LLMs","created":"2025-05-20","cited_by_count":129,"area":null},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124,"area":"alignment"},{"id":"2310.15819","title":"Generative Language Models Exhibit Social Identity Biases","created":"2023-10-24","cited_by_count":111,"area":null},{"id":"2502.08177","title":"SycEval: Evaluating LLM Sycophancy","created":"2025-02-12","cited_by_count":108,"area":null},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2505.23840","title":"Measuring Sycophancy of Language Models in Multi-turn Dialogues","created":"2025-05-28","cited_by_count":104,"area":null},{"id":"2411.15287","title":"Sycophancy in Large Language Models: Causes and Mitigations","created":"2024-11-22","cited_by_count":101,"area":null},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"area":null},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2311.11829","title":"System 2 Attention (is something you might need too)","created":"2023-11-20","cited_by_count":89,"area":null},{"id":"2311.08596","title":"Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment","created":"2023-11-14","cited_by_count":77,"area":null},{"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":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2410.24190","title":"Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters","created":"2024-10-31","cited_by_count":71,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2402.02420","title":"Factuality of Large Language Models: A Survey","created":"2024-02-04","cited_by_count":66,"area":null},{"id":"2401.00820","title":"A Computational Framework for Behavioral Assessment of LLM Therapists","created":"2024-01-01","cited_by_count":62,"area":null},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"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":"2604.07729","title":"Emotion Concepts and their Function in a Large Language Model","created":"2026-04-09","cited_by_count":57,"area":null},{"id":"2409.01658","title":"From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning","created":"2024-09-03","cited_by_count":54,"area":null},{"id":"2407.07880","title":"Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization","created":"2024-07-10","cited_by_count":53,"area":"alignment"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2406.14805","title":"How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions","created":"2024-06-21","cited_by_count":52,"area":null},{"id":"2410.19750","title":"The Geometry of Concepts: Sparse Autoencoder Feature Structure","created":"2024-10-10","cited_by_count":52,"area":"mechinterp"},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"id":"2506.00103","title":"Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards","created":"2025-05-30","cited_by_count":50,"area":"alignment"},{"id":"2508.02087","title":"When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models","created":"2025-08-04","cited_by_count":50,"area":null},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2402.13220","title":"How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts","created":"2024-02-20","cited_by_count":47,"area":"mllm"},{"id":"2403.04893","title":"A Safe Harbor for AI Evaluation and Red Teaming","created":"2024-03-07","cited_by_count":47,"area":"safety"},{"id":"2411.02306","title":"On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback","created":"2024-11-04","cited_by_count":47,"area":"alignment"},{"id":"2502.02528","title":"Why human-AI relationships need socioaffective alignment","created":"2025-02-04","cited_by_count":47,"area":null},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2311.08702","title":"Debate Helps Supervise Unreliable Experts","created":"2023-11-15","cited_by_count":43,"area":null},{"id":"2402.14433","title":"A Language Model's Guide Through Latent Space","created":"2024-02-22","cited_by_count":43,"area":null},{"id":"2406.19501","title":"Monitoring Latent World States in Language Models with Propositional Probes","created":"2024-06-27","cited_by_count":43,"area":"wm"},{"id":"2510.05024","title":"Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment","created":"2025-10-06","cited_by_count":43,"area":"alignment"},{"id":"2412.14959","title":"Understanding the Dark Side of LLMs' Intrinsic Self-Correction","created":"2024-12-19","cited_by_count":42,"area":"lr"},{"id":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42,"area":"alignment"},{"id":"2402.12715","title":"The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning","created":"2024-02-20","cited_by_count":41,"area":null},{"id":"2406.06560","title":"Inverse Constitutional AI: Compressing Preferences into Principles","created":"2024-06-02","cited_by_count":41,"area":"alignment"},{"id":"2403.05518","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","created":"2024-03-08","cited_by_count":39,"area":"lr"},{"id":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39,"area":"agents"},{"id":"2502.16534","title":"Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs","created":"2025-02-23","cited_by_count":39,"area":null},{"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":"2406.15053","title":"PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data","created":"2024-06-21","cited_by_count":37,"area":null},{"id":"2509.21305","title":"Sycophancy Is Not One Thing: Causal Separation of Sycophantic Behaviors in LLMs","created":"2025-09-25","cited_by_count":37,"area":null},{"id":"2509.03730","title":"The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs","created":"2025-09-03","cited_by_count":36,"area":null},{"id":"2410.12428","title":"Conformity in Large Language Models","created":"2024-10-16","cited_by_count":34,"area":null},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"id":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34,"area":"alignment"},{"id":"2405.17713","title":"AI Alignment with Changing and Influenceable Reward Functions","created":"2024-05-28","cited_by_count":33,"area":"alignment"},{"id":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33,"area":null},{"id":"2411.03814","title":"MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue","created":"2024-11-06","cited_by_count":33,"area":"agents"},{"id":"2503.05659","title":"A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval","created":"2025-03-07","cited_by_count":33,"area":"agents"},{"id":"2503.11656","title":"TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models","created":"2025-02-04","cited_by_count":33,"area":null},{"id":"2405.19479","title":"Participation in the age of foundation models","created":"2024-05-29","cited_by_count":32,"area":null},{"id":"2503.02080","title":"Linear Representations of Political Perspective Emerge in Large Language Models","created":"2025-03-03","cited_by_count":32,"area":"mechinterp"},{"id":"2506.01926","title":"Large language models can learn and generalize steganographic chain-of-thought under process supervision","created":"2025-06-02","cited_by_count":32,"area":"lr"},{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2409.03219","title":"Content Moderation by LLM: From Accuracy to Legitimacy","created":"2024-09-05","cited_by_count":30,"area":null},{"id":"2506.05598","title":"SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs","created":"2025-06-05","cited_by_count":29,"area":"alignment"},{"id":"2509.23055","title":"Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate","created":"2025-09-27","cited_by_count":29,"area":"agents"},{"id":"2312.14302","title":"Exploiting Novel GPT-4 APIs","created":"2023-12-21","cited_by_count":28,"area":"agents"},{"id":"2410.16251","title":"Can Knowledge Editing Really Correct Hallucinations?","created":"2024-10-21","cited_by_count":28,"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":"2409.01754","title":"Empirical evidence of Large Language Model's influence on human spoken communication","created":"2024-09-03","cited_by_count":27,"area":null},{"id":"2411.12405","title":"Evaluating the Prompt Steerability of Large Language Models","created":"2024-11-19","cited_by_count":27,"area":null},{"id":"2502.12964","title":"Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer","created":"2025-02-18","cited_by_count":27,"area":null},{"id":"2510.04721","title":"BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs","created":"2025-10-06","cited_by_count":27,"area":null},{"id":"2602.14069","title":"Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric","created":"2026-02-15","cited_by_count":27,"area":"alignment"},{"id":"2501.05171","title":"Emergence of polarization in networks of large language model agents","created":"2025-01-09","cited_by_count":26,"area":"agents"},{"id":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"area":"alignment"},{"id":"2406.13261","title":"BeHonest: Benchmarking Honesty in Large Language Models","created":"2024-06-19","cited_by_count":24,"area":null},{"id":"2406.19354","title":"Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?","created":"2024-06-27","cited_by_count":24,"area":null},{"id":"2412.03578","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","created":"2024-11-18","cited_by_count":24,"area":null},{"id":"2404.16251","title":"Prompt Leakage effect and defense strategies for multi-turn LLM interactions","created":"2024-04-24","cited_by_count":23,"area":null},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2601.16644","title":"Sycophancy Hides Linearly in the Attention Heads","created":"2026-01-23","cited_by_count":23,"area":null},{"id":"2602.01002","title":"How RLHF Amplifies Sycophancy","created":"2026-02-01","cited_by_count":23,"area":"alignment"},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2510.19851","title":"Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability","created":"2025-10-21","cited_by_count":22,"area":"lr"},{"id":"2601.13722","title":"OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents","created":"2026-01-20","cited_by_count":22,"area":"agents"},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null}],"next_cursor":"100"}