{"total":121,"rows":[{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2502.18864","title":"Accelerating scientific discovery with Co-Scientist","created":"2025-02-26","cited_by_count":401,"area":null},{"id":"2406.07791","title":"Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge","created":"2024-06-12","cited_by_count":269,"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":"2406.14711","title":"MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate","created":"2024-06-20","cited_by_count":56,"area":null},{"id":"2410.21514","title":"Sabotage Evaluations for Frontier Models","created":"2024-10-28","cited_by_count":52,"area":null},{"id":"2502.14815","title":"Optimizing Model Selection for Compound AI Systems","created":"2025-02-20","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":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33,"area":null},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32,"area":null},{"id":"2406.00936","title":"A Survey of Useful LLM Evaluation","created":"2024-06-03","cited_by_count":29,"area":null},{"id":"2511.01805","title":"Accumulating Context Changes the Beliefs of Language Models","created":"2025-11-03","cited_by_count":28,"area":null},{"id":"2408.09235","title":"Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form QA","created":"2024-08-17","cited_by_count":25,"area":null},{"id":"2406.11044","title":"Evaluating the Performance of Large Language Models via Debates","created":"2024-06-16","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":"2409.17213","title":"Plurals: A System for Guiding LLMs Via Simulated Social Ensembles","created":"2024-09-25","cited_by_count":17,"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":"2503.14481","title":"Don't lie to your friends: Learning what you know from collaborative self-play","created":"2025-03-18","cited_by_count":14,"area":null},{"id":"2506.13609","title":"Avoiding Obfuscation with Prover-Estimator Debate","created":"2025-06-16","cited_by_count":14,"area":null},{"id":"2404.12545","title":"Latent Concept-based Explanation of NLP Models","created":"2024-04-18","cited_by_count":13,"area":null},{"id":"2502.08550","title":"No Need for Explanations: LLMs can implicitly learn from mistakes in-context","created":"2025-02-12","cited_by_count":13,"area":null},{"id":"2603.00039","title":"CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation","created":"2026-02-09","cited_by_count":13,"area":null},{"id":"2411.03665","title":"Evaluating Moral Beliefs across LLMs through a Pluralistic Framework","created":"2024-11-06","cited_by_count":11,"area":null},{"id":"2506.00549","title":"Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages","created":"2025-05-31","cited_by_count":11,"area":null},{"id":"2406.14760","title":"An LLM Feature-based Framework for Dialogue Constructiveness Assessment","created":"2024-06-20","cited_by_count":9,"area":null},{"id":"2507.16196","title":"Do Large Language Models Have a Planning Theory of Mind? Evidence from MindGames: a Multi-Step Persuasion Task","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2407.04183","title":"Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Norms","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2410.13517","title":"Bias in the Mirror: Are LLMs opinions robust to their own adversarial attacks ?","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2501.13124","title":"Debate Helps Weak-to-Strong Generalization","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2607.08535","title":"When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability","created":"2026-07-09","cited_by_count":8,"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":"2507.17747","title":"Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2503.08542","title":"CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2505.00003","title":"A Review of Incorporating Psychological Theories in LLMs","created":"2025-03-28","cited_by_count":6,"area":null},{"id":"2606.00424","title":"Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight","created":"2026-05-29","cited_by_count":6,"area":null},{"id":"2606.30571","title":"Attractor States Emerge in Multi-Turn LLM Conversations","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2505.21537","title":"OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of Large Language Models","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2506.00178","title":"Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2507.01936","title":"The Thin Line Between Comprehension and Persuasion in LLMs","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2512.04068","title":"Learning Steerable Clarification Policies with Collaborative Self-play","created":"2025-12-03","cited_by_count":5,"area":null},{"id":"2606.16475","title":"AI systems out-persuade expert humans","created":"2026-06-15","cited_by_count":5,"area":null},{"id":"2502.00322","title":"MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections","created":"2025-02-01","cited_by_count":4,"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":"2510.21332","title":"Weak-to-Strong Generalization under Distribution Shifts","created":"2025-10-24","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":"2406.17809","title":"Towards a Science Exocortex","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2410.01064","title":"Truth or Deceit? A Bayesian Decoding Game Enhances Consistency and Reliability","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2503.05328","title":"Dynamic Knowledge Integration for Evidence-Driven Counter-Argument Generation with Large Language Models","created":"2025-03-07","cited_by_count":3,"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":"2504.03731","title":"A Benchmark for Scalable Oversight Protocols","created":"2025-03-31","cited_by_count":3,"area":null},{"id":"2506.06020","title":"When to Trust Context: Self-Reflective Debates for Context Reliability","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2508.02584","title":"MArgE: Meshing Argumentative Evidence from Multiple Large Language Models for Justifiable Claim Verification","created":"2025-08-04","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":"2602.11483","title":"Understanding Persuasive Interactions between Generative Social Agents and Humans: The Knowledge-based Persuasion Model (KPM)","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2602.22752","title":"Towards Simulating Social Media Users with LLMs: Evaluating the Operational Validity of Conditioned Comment Prediction","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2604.21564","title":"Measuring Opinion Bias and Sycophancy via LLM-based Persuasion","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2410.13215","title":"Balancing Label Quantity and Quality for Scalable Elicitation","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2504.07385","title":"SAGE: A Search-AuGmented Evaluation of Large Language Models on Free-Form QA","created":"2025-04-10","cited_by_count":2,"area":null},{"id":"2505.16648","title":"Collaboration among Multiple Large Language Models for Medical Question Answering","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2506.13245","title":"A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2507.02595","title":"MPF: Aligning and Debiasing Language Models post Deployment via Multi Perspective Fusion","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2509.06858","title":"Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2510.06307","title":"Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2511.02495","title":"DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding","created":"2025-11-04","cited_by_count":2,"area":null},{"id":"2511.09139","title":"MACEval: A Multi-Agent Continual Evaluation Network for Large Models","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2511.14098","title":"Collaborative QA using Interacting LLMs. Impact of Network Structure, Node Capability and Distributed Data","created":"2025-11-18","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":"2602.04003","title":"When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2606.17657","title":"Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2502.13410","title":"Tell Me Why: Incentivizing Explanations","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2505.02888","title":"When Your Own Output Becomes Your Training Data: Noise-to-Meaning Loops and a Formal RSI Trigger","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2505.12259","title":"Teach2Eval: An Indirect Evaluation Method for LLM by Judging How It Teaches","created":"2025-05-18","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":"2508.04511","title":"Argumentative Debates for Transparent Bias Detection [Technical Report]","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2510.08145","title":"Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2602.00970","title":"Verification Required: The Impact of Information Credibility on AI Persuasion","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2602.21556","title":"Power and Limitations of Aggregation in Compound AI Systems","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2604.17366","title":"ArgBench: Benchmarking LLMs on Computational Argumentation Tasks","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2604.18951","title":"Superficial Success vs. Internal Breakdown: An Empirical Study of Generalization in Adaptive Multi-Agent Systems","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.05592","title":"When Can Voting Help, Hurt, or Change Course? Exact Structure of Binary Test-Time Aggregation","created":"2026-05-07","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":"2606.08098","title":"When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2607.27499","title":"A dataset of rated conceptual arguments","created":"2026-07-29","cited_by_count":1,"area":null},{"id":"2608.11247","title":"Conformity Mitigations in Large Language Models Lie on a Single Resistance-Receptivity Frontier","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2406.02795","title":"ArguMentor: Augmenting User Experiences with Counter-Perspectives","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2408.16331","title":"Guided Reasoning: A Non-Technical Introduction","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2409.11052","title":"A logical alarm for misaligned binary classifiers","created":"2024-09-17","cited_by_count":0,"area":null},{"id":"2409.15867","title":"In-Context Ensemble Learning from Pseudo Labels Improves Video-Language Models for Low-Level Workflow Understanding","created":"2024-09-24","cited_by_count":0,"area":null},{"id":"2412.16238","title":"Algebraic Evaluation Theorems","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2502.12921","title":"Q-STRUM Debate: Query-Driven Contrastive Summarization for Recommendation Comparison","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2502.18874","title":"Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2506.05876","title":"Information Bargaining: Bilateral Commitment in Bayesian Persuasion","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2506.18213","title":"A Conceptual Framework for AI Capability Evaluations","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2508.08265","title":"TurQUaz at CheckThat! 2025: Debating Large Language Models for Scientific Web Discourse Detection","created":"2025-07-26","cited_by_count":0,"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":"2510.22500","title":"Towards Scalable Oversight via Partitioned Human Supervision","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2512.06227","title":"Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safety","created":"2025-12-06","cited_by_count":0,"area":null}],"next_cursor":"100"}