{"list":"other","total":52,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2312.08935","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","created":"2023-12-14","cited_by_count":928},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367},{"id":"2310.17631","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","created":"2023-10-26","cited_by_count":367},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316},{"id":"2306.17563","title":"Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting","created":"2023-06-30","cited_by_count":307},{"id":"2106.01144","title":"Towards Emotional Support Dialog Systems","created":"2021-06-02","cited_by_count":299},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238},{"id":"2210.13312","title":"Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs","created":"2022-10-24","cited_by_count":220},{"id":"2402.06457","title":"V-STaR: Training Verifiers for Self-Taught Reasoners","created":"2024-02-09","cited_by_count":217},{"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},{"id":"2310.17976","title":"InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews","created":"2023-10-27","cited_by_count":179},{"id":"2310.15421","title":"FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions","created":"2023-10-24","cited_by_count":171},{"id":"2305.14763","title":"Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models","created":"2023-05-24","cited_by_count":163},{"id":"2403.16950","title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","created":"2024-03-25","cited_by_count":149},{"id":"2401.03601","title":"InFoBench: Evaluating Instruction Following Ability in Large Language Models","created":"2024-01-07","cited_by_count":135},{"id":"2310.15123","title":"Branch-Solve-Merge Improves Large Language Model Evaluation and Generation","created":"2023-10-23","cited_by_count":106},{"id":"2407.04622","title":"On scalable oversight with weak LLMs judging strong LLMs","created":"2024-07-05","cited_by_count":99},{"id":"2407.06551","title":"OffsetBias: Leveraging Debiased Data for Tuning Evaluators","created":"2024-07-09","cited_by_count":94},{"id":"2403.08715","title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents","created":"2024-03-13","cited_by_count":93},{"id":"2312.06281","title":"EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models","created":"2023-12-11","cited_by_count":80},{"id":"2407.00870","title":"Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles","created":"2024-07-01","cited_by_count":73},{"id":"2310.16755","title":"HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models","created":"2023-10-25","cited_by_count":63},{"id":"2411.16579","title":"Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision","created":"2024-11-25","cited_by_count":60},{"id":"2307.09042","title":"Emotional Intelligence of Large Language Models","created":"2023-07-18","cited_by_count":58},{"id":"2309.12309","title":"Rehearsal: Simulating Conflict to Teach Conflict Resolution","created":"2023-09-21","cited_by_count":55},{"id":"2402.12071","title":"EmoBench: Evaluating the Emotional Intelligence of Large Language Models","created":"2024-02-19","cited_by_count":53},{"id":"2009.09708","title":"Knowledge Bridging for Empathetic Dialogue Generation","created":"2020-09-21","cited_by_count":50},{"id":"2504.19162","title":"SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning","created":"2025-04-27","cited_by_count":42},{"id":"2410.19346","title":"AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios","created":"2024-10-25","cited_by_count":40},{"id":"2311.16832","title":"CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models","created":"2023-11-28","cited_by_count":34},{"id":"2307.02768","title":"Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts","created":"2023-07-06","cited_by_count":31},{"id":"2502.11451","title":"From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support Conversations","created":"2025-02-17","cited_by_count":23},{"id":"2208.08845","title":"CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation","created":"2022-08-18","cited_by_count":18},{"id":"2307.07994","title":"Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning Approach","created":"2023-07-16","cited_by_count":15},{"id":"2404.04204","title":"Social Skill Training with Large Language Models","created":"2024-04-05","cited_by_count":15},{"id":"2502.08922","title":"Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models","created":"2025-02-13","cited_by_count":13},{"id":"2503.17363","title":"Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique","created":"2025-03-21","cited_by_count":13},{"id":"2403.06591","title":"Academically intelligent LLMs are not necessarily socially intelligent","created":"2024-03-11","cited_by_count":12},{"id":"2504.17238","title":"Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues","created":"2025-04-24","cited_by_count":11},{"id":"2501.09993","title":"Agent-as-Judge for Factual Summarization of Long Narratives","created":"2025-01-17","cited_by_count":9},{"id":"2504.01495","title":"Are Autonomous Web Agents Good Testers?","created":"2025-04-02","cited_by_count":6}],"next_cursor":null}