{"total":23,"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":"2407.04622","title":"On scalable oversight with weak LLMs judging strong LLMs","created":"2024-07-05","cited_by_count":99,"area":null},{"id":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85,"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":"2506.13609","title":"Avoiding Obfuscation with Prover-Estimator Debate","created":"2025-06-16","cited_by_count":14,"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":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2502.18018","title":"Verdict: A Library for Scaling Judge-Time Compute","created":"2025-02-25","cited_by_count":7,"area":null},{"id":"2510.13912","title":"AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2605.25133","title":"Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2605.29601","title":"Training Deliberative Monitors for Black-Box Scheming Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2503.22989","title":"FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2504.06549","title":"Societal Impacts Research Requires Benchmarks for Creative Composition Tasks","created":"2025-04-09","cited_by_count":3,"area":null},{"id":"2506.17846","title":"Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)","created":"2025-06-21","cited_by_count":3,"area":null},{"id":"2510.26518","title":"Human-AI Complementarity: A Goal for Amplified Oversight","created":"2025-10-30","cited_by_count":3,"area":null},{"id":"2502.13410","title":"Tell Me Why: Incentivizing Explanations","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2504.07316","title":"Alice: Proactive Learning with Teacher's Demonstrations for Weak-to-Strong Generalization","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2505.14015","title":"AUTOLAW: Enhancing Legal Compliance in Large Language Models via Case Law Generation and Jury-Inspired Deliberation","created":"2025-05-20","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":"2510.05909","title":"Optimizing for Persuasion Improves LLM Generalization: Evidence from Quality-Diversity Evolution of Debate Strategies","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2601.05904","title":"Can AI mediation improve democratic deliberation?","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2609.24895","title":"Human-LLM Deliberation as Interactive Proof: Conditions for Verifiability Without Transparency","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.02557","title":"How to Have a Sensitive Debate: An Instance-Optimal Protocol for AI Debate","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}