{"total":48,"rows":[{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"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":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2601.16644","title":"Sycophancy Hides Linearly in the Attention Heads","created":"2026-01-23","cited_by_count":23,"area":null},{"id":"2411.11504","title":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering","created":"2024-11-18","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":"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":"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":"2512.19027","title":"Recontextualization Mitigates Specification Gaming without Modifying the Specification","created":"2025-12-22","cited_by_count":14,"area":null},{"id":"2410.15512","title":"Reverse Question Answering: Can an LLM Write a Question so Hard (or Bad) that it Can't Answer?","created":"2024-10-20","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":"2504.13959","title":"AI Safety Should Prioritize the Future of Work","created":"2025-04-16","cited_by_count":11,"area":null},{"id":"2506.10139","title":"Unsupervised Elicitation of Language Models","created":"2025-06-11","cited_by_count":11,"area":null},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"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":"2511.17408","title":"The Impact of Off-Policy Training Data on Probe Generalisation","created":"2025-11-21","cited_by_count":9,"area":null},{"id":"2502.14445","title":"PredictaBoard: Benchmarking LLM Score Predictability","created":"2025-02-20","cited_by_count":7,"area":null},{"id":"2507.07484","title":"Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models","created":"2025-07-10","cited_by_count":7,"area":null},{"id":"2603.00024","title":"Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2412.17797","title":"Observation Interference in Partially Observable Assistance Games","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2409.18170","title":"Evaluation of Large Language Models for Summarization Tasks in the Medical Domain: A Narrative Review","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2502.12436","title":"Should I Trust You? Detecting Deception in Negotiations using Counterfactual RL","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2605.04431","title":"Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2410.23331","title":"Can Models Help Us Create Better Models? Evaluating LLMs as Data Scientists","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2509.23095","title":"Causally-Enhanced Reinforcement Policy Optimization","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2601.20299","title":"Truthfulness Despite Weak Supervision: Evaluating and Training LLMs Using Peer Prediction","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2603.00883","title":"Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2505.21478","title":"Policy Optimized Text-to-Image Pipeline Design","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2506.19783","title":"SAGE: Strategy-Adaptive Generation Engine for Query Rewriting","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2510.25662","title":"User Misconceptions of LLM-Based Conversational Programming Assistants","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2604.24444","title":"Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2605.27483","title":"Debate Helps Weak Judges Reward Stronger Models","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2607.20146","title":"Gotta Catch them all: the modes of Sycophancy","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2608.00220","title":"Verifier-Induced Support Reshaping in On-Policy Optimization","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2601.15130","title":"The Plausibility Trap: Using Probabilistic Engines for Deterministic Tasks","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2602.17676","title":"Epistemic Traps: Rational Misalignment Driven by Model Misspecification","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.20400","title":"Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.04820","title":"Autoscoring Anticlimax: A Meta-analytic Understanding of AI's Short-answer Shortcomings and Wording Weaknesses","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.12500","title":"Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.10601","title":"The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.28814","title":"Rolling With Resistance: Preference-Optimized LLM Counselors Can Trade Goal Persistence for Relational Attunement in Motivational Interviewing","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.23311","title":"Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.33150","title":"Generalization Dynamics of LM Pre-training","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34198","title":"Frozen Judges, Moving Agents: Version-Dependent LLM-Judge Error and the Limits of Judge-Assisted Agent Evaluation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.15938","title":"The Anatomy of a Blind Spot: What an LLM Judge Must Be Shown, and How Much","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.16070","title":"Understanding and Reducing Misalignment in Persuasion Optimization","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}