{"list":"other","total":52,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2308.07201","title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","created":"2023-08-14","cited_by_count":742},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"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":"2207.00032","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","created":"2022-06-30","cited_by_count":407},{"id":"2410.02736","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","created":"2024-10-03","cited_by_count":368},{"id":"2310.17631","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","created":"2023-10-26","cited_by_count":367},{"id":"2410.18451","title":"Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs","created":"2024-10-24","cited_by_count":327},{"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":"2310.07641","title":"Evaluating Large Language Models at Evaluating Instruction Following","created":"2023-10-11","cited_by_count":302},{"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":"2507.01352","title":"Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy","created":"2025-07-02","cited_by_count":214},{"id":"2410.16184","title":"RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style","created":"2024-10-21","cited_by_count":176},{"id":"2310.05470","title":"Generative Judge for Evaluating Alignment","created":"2023-10-09","cited_by_count":169},{"id":"2505.02387","title":"RM-R1: Reward Modeling as Reasoning","created":"2025-05-05","cited_by_count":154},{"id":"2309.17012","title":"Benchmarking Cognitive Biases in Large Language Models as Evaluators","created":"2023-09-29","cited_by_count":150},{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150},{"id":"2406.10216","title":"Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs","created":"2024-06-14","cited_by_count":142},{"id":"2402.07319","title":"ODIN: Disentangled Reward Mitigates Hacking in RLHF","created":"2024-02-11","cited_by_count":136},{"id":"2403.02839","title":"An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4","created":"2024-03-05","cited_by_count":94},{"id":"2407.06551","title":"OffsetBias: Leveraging Debiased Data for Tuning Evaluators","created":"2024-07-09","cited_by_count":94},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79},{"id":"2504.00050","title":"JudgeLRM: Large Reasoning Models as a Judge","created":"2025-03-31","cited_by_count":78},{"id":"2409.13156","title":"RRM: Robust Reward Model Training Mitigates Reward Hacking","created":"2024-09-20","cited_by_count":76},{"id":"2505.10320","title":"J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning","created":"2025-05-15","cited_by_count":75},{"id":"2505.11475","title":"HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages","created":"2025-05-16","cited_by_count":75},{"id":"2410.09893","title":"RMB: Comprehensively Benchmarking Reward Models in LLM Alignment","created":"2024-10-13","cited_by_count":61},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53},{"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":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42},{"id":"2504.09946","title":"Assessing Judging Bias in Large Reasoning Models: An Empirical Study","created":"2025-04-14","cited_by_count":30},{"id":"2501.17195","title":"Atla Selene Mini: A General Purpose Evaluation Model","created":"2025-01-27","cited_by_count":27},{"id":"2506.14175","title":"GRAM: A Generative Foundation Reward Model for Reward Generalization","created":"2025-06-17","cited_by_count":25},{"id":"2512.16041","title":"Are We on the Right Way to Assessing LLM-as-a-Judge?","created":"2025-12-17","cited_by_count":24},{"id":"2505.14268","title":"Think-J: Learning to Think for Generative LLM-as-a-Judge","created":"2025-05-20","cited_by_count":21},{"id":"2409.16788","title":"Mitigating the Bias of Large Language Model Evaluation","created":"2024-09-25","cited_by_count":17},{"id":"2505.17100","title":"Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector","created":"2025-05-21","cited_by_count":14},{"id":"2505.13487","title":"Detecting Prefix Bias in LLM-based Reward Models","created":"2025-05-13","cited_by_count":11},{"id":"2505.19477","title":"Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge","created":"2025-05-26","cited_by_count":11},{"id":"2601.14032","title":"RM-Distiller: Exploiting Generative LLM for Reward Model Distillation","created":"2026-01-20","cited_by_count":2}],"next_cursor":null}