{"list":"other","total":65,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2404.04475","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","created":"2024-04-06","cited_by_count":897},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"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":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"2004.13637","title":"Recipes for building an open-domain chatbot","created":"2020-04-28","cited_by_count":593},{"id":"2310.08491","title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","created":"2023-10-12","cited_by_count":575},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446},{"id":"2410.02736","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","created":"2024-10-03","cited_by_count":368},{"id":"2404.18796","title":"Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models","created":"2024-04-29","cited_by_count":326},{"id":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323},{"id":"2410.12784","title":"JudgeBench: A Benchmark for Evaluating LLM-based Judges","created":"2024-10-16","cited_by_count":318},{"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},{"id":"2406.18403","title":"LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks","created":"2024-06-26","cited_by_count":243},{"id":"2209.13085","title":"Defining and Characterizing Reward Hacking","created":"2022-09-27","cited_by_count":203},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201},{"id":"2308.03958","title":"Simple synthetic data reduces sycophancy in large language models","created":"2023-08-07","cited_by_count":187},{"id":"2406.10162","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","created":"2024-06-14","cited_by_count":178},{"id":"2310.00746","title":"RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models","created":"2023-10-01","cited_by_count":175},{"id":"2306.04181","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","created":"2023-06-07","cited_by_count":172},{"id":"2309.17012","title":"Benchmarking Cognitive Biases in Large Language Models as Evaluators","created":"2023-09-29","cited_by_count":150},{"id":"1803.04585","title":"Categorizing Variants of Goodhart's Law","created":"2018-03-13","cited_by_count":149},{"id":"2211.02570","title":"The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation","created":"2022-11-04","cited_by_count":139},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109},{"id":"2309.17167","title":"DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks","created":"2023-09-29","cited_by_count":101},{"id":"2407.06551","title":"OffsetBias: Leveraging Debiased Data for Tuning Evaluators","created":"2024-07-09","cited_by_count":94},{"id":"2501.00274","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts","created":"2024-12-31","cited_by_count":87},{"id":"2306.11247","title":"DICES Dataset: Diversity in Conversational AI Evaluation for Safety","created":"2023-06-20","cited_by_count":86},{"id":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85},{"id":"2401.16745","title":"MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models","created":"2024-01-30","cited_by_count":81},{"id":"2101.07714","title":"Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach","created":"2021-01-19","cited_by_count":75},{"id":"2402.11443","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation","created":"2024-02-18","cited_by_count":75},{"id":"2410.03608","title":"TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation","created":"2024-10-04","cited_by_count":68},{"id":"2504.20879","title":"The Leaderboard Illusion","created":"2025-04-29","cited_by_count":66},{"id":"2309.13567","title":"MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models","created":"2023-09-24","cited_by_count":63},{"id":"2505.15055","title":"Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory","created":"2025-05-21","cited_by_count":45},{"id":"2407.08351","title":"AutoBencher: Towards Declarative Benchmark Construction","created":"2024-07-11","cited_by_count":44},{"id":"2503.13509","title":"MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance","created":"2025-03-13","cited_by_count":39},{"id":"2506.08584","title":"CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering","created":"2025-06-10","cited_by_count":21},{"id":"2602.08672","title":"Learning to Judge: LLMs Designing and Applying Evaluation Rubrics","created":"2026-02-09","cited_by_count":19},{"id":"2601.19922","title":"HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue","created":"2026-01-09","cited_by_count":13},{"id":"2604.23178","title":"Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipelines","created":"2026-04-25","cited_by_count":8},{"id":"2509.09711","title":"PsychiatryBench: A Multi-Task Benchmark for LLMs in Psychiatry","created":"2025-09-07","cited_by_count":6},{"id":"2601.18630","title":"Assessing the Quality of Mental Health Support in LLM Responses through Multi-Attribute Human Evaluation","created":"2026-01-26","cited_by_count":6},{"id":"2510.08569","title":"ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation","created":"2025-10-09","cited_by_count":2},{"id":"2505.13480","title":"Evaluating Reasoning LLMs for Suicide Screening with the Columbia-Suicide Severity Rating Scale","created":"2025-05-11","cited_by_count":1}],"next_cursor":null}