{"total":579,"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":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"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":"2401.01301","title":"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models","created":"2024-01-02","cited_by_count":150,"area":null},{"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":"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":"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":"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":"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":"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":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"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":"2502.02528","title":"Why human-AI relationships need socioaffective alignment","created":"2025-02-04","cited_by_count":47,"area":null},{"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":"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":"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":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33,"area":null},{"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":"2409.03219","title":"Content Moderation by LLM: From Accuracy to Legitimacy","created":"2024-09-05","cited_by_count":30,"area":null},{"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":"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":"2601.16644","title":"Sycophancy Hides Linearly in the Attention Heads","created":"2026-01-23","cited_by_count":23,"area":null},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2403.15115","title":"Language Models in Dialogue: Conversational Maxims for Human-AI Interactions","created":"2024-03-22","cited_by_count":21,"area":null},{"id":"2405.06800","title":"LLM-Generated Black-box Explanations Can Be Adversarially Helpful","created":"2024-05-10","cited_by_count":21,"area":null},{"id":"2507.21919","title":"Training language models to be warm and empathetic makes them less reliable and more sycophantic","created":"2025-07-29","cited_by_count":21,"area":null},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2504.15784","title":"Automated Creativity Evaluation for Large Language Models: A Reference-Based Approach","created":"2025-04-22","cited_by_count":20,"area":null},{"id":"2511.05408","title":"Steering Language Models with Weight Arithmetic","created":"2025-11-07","cited_by_count":20,"area":null},{"id":"2404.09971","title":"Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs","created":"2024-04-15","cited_by_count":19,"area":null},{"id":"2405.11100","title":"Are Large Language Models Moral Hypocrites? A Study Based on Moral Foundations","created":"2024-05-17","cited_by_count":19,"area":null},{"id":"2406.04214","title":"ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2410.14596","title":"Teaching Models to Balance Resisting and Accepting Persuasion","created":"2024-10-18","cited_by_count":19,"area":null},{"id":"2505.21091","title":"Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)","created":"2025-05-27","cited_by_count":19,"area":null},{"id":"2510.15501","title":"DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios","created":"2025-10-17","cited_by_count":19,"area":null},{"id":"2410.14746","title":"Accounting for Sycophancy in Language Model Uncertainty Estimation","created":"2024-10-17","cited_by_count":18,"area":null},{"id":"2503.09598","title":"How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation","created":"2025-03-12","cited_by_count":18,"area":null},{"id":"2507.18905","title":"Large language models provide unsafe answers to patient-posed medical questions","created":"2025-07-25","cited_by_count":18,"area":null},{"id":"2508.13743","title":"Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA","created":"2025-08-19","cited_by_count":18,"area":null},{"id":"2602.11865","title":"Intelligent AI Delegation","created":"2026-02-12","cited_by_count":18,"area":null},{"id":"2409.17213","title":"Plurals: A System for Guiding LLMs Via Simulated Social Ensembles","created":"2024-09-25","cited_by_count":17,"area":null},{"id":"2410.13961","title":"From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization","created":"2024-10-17","cited_by_count":17,"area":null},{"id":"2409.12538","title":"PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research Ideation","created":"2024-09-19","cited_by_count":16,"area":null},{"id":"2504.11844","title":"Evaluating the Goal-Directedness of Large Language Models","created":"2025-04-16","cited_by_count":16,"area":null},{"id":"2505.03989","title":"An alignment safety case sketch based on debate","created":"2025-05-06","cited_by_count":16,"area":null},{"id":"2506.06485","title":"Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflict","created":"2025-06-06","cited_by_count":16,"area":null},{"id":"2605.21778","title":"What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct","created":"2026-05-20","cited_by_count":16,"area":null},{"id":"2406.05494","title":"Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation","created":"2024-06-08","cited_by_count":15,"area":null},{"id":"2406.17737","title":"LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users","created":"2024-06-25","cited_by_count":15,"area":null},{"id":"2410.11302","title":"Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs","created":"2024-10-15","cited_by_count":15,"area":null},{"id":"2412.02802","title":"Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model","created":"2024-12-03","cited_by_count":15,"area":null},{"id":"2507.19218","title":"Technological folie \\`a deux: Feedback Loops Between AI Chatbots and Mental Illness","created":"2025-07-25","cited_by_count":15,"area":null},{"id":"2510.06124","title":"Taxonomy of User Needs and Actions","created":"2025-10-07","cited_by_count":15,"area":null},{"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":"2311.09542","title":"Pregnant Questions: The Importance of Pragmatic Awareness in Maternal Health Question Answering","created":"2023-11-16","cited_by_count":14,"area":null},{"id":"2407.18008","title":"GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy","created":"2024-07-25","cited_by_count":14,"area":null},{"id":"2410.22071","title":"Distinguishing Ignorance from Error in LLM Hallucinations","created":"2024-10-29","cited_by_count":14,"area":null},{"id":"2501.05382","title":"Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2504.01205","title":"Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2402.12590","title":"Evolving AI Collectives to Enhance Human Diversity and Enable Self-Regulation","created":"2024-02-19","cited_by_count":13,"area":null},{"id":"2412.16746","title":"Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Models","created":"2024-12-21","cited_by_count":13,"area":null},{"id":"2503.22353","title":"Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions","created":"2025-03-28","cited_by_count":13,"area":null},{"id":"2505.07775","title":"Must Read: A Comprehensive Survey of Computational Persuasion","created":"2025-05-12","cited_by_count":13,"area":null},{"id":"2508.16846","title":"BASIL: Bayesian Assessment of Sycophancy in LLMs","created":"2025-08-23","cited_by_count":13,"area":null},{"id":"2508.17450","title":"Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD","created":"2025-08-24","cited_by_count":13,"area":null},{"id":"2509.08010","title":"Measuring and mitigating overreliance to build human-compatible AI","created":"2025-09-08","cited_by_count":12,"area":null},{"id":"2602.14270","title":"A Rational Analysis of the Effects of Sycophantic AI","created":"2026-02-15","cited_by_count":12,"area":null},{"id":"2602.15515","title":"The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2509.08494","title":"HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants","created":"2025-09-10","cited_by_count":11,"area":null}],"next_cursor":"100"}