{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2409.12186","title":"Qwen2.5-Coder Technical Report","created":"2024-09-18","cited_by_count":1203},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"1804.06561","title":"A Mean Field View of the Landscape of Two-Layers Neural Networks","created":"2018-04-18","cited_by_count":466},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316},{"id":"2212.09561","title":"Large Language Models are Better Reasoners with Self-Verification","created":"2022-12-19","cited_by_count":307},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264},{"id":"2310.02743","title":"Reward Model Ensembles Help Mitigate Overoptimization","created":"2023-10-04","cited_by_count":231},{"id":"2312.09244","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","created":"2023-12-14","cited_by_count":200},{"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":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147},{"id":"2412.01951","title":"Self-Improvement in Language Models: The Sharpening Mechanism","created":"2024-12-02","cited_by_count":104},{"id":"1904.00687","title":"On the Power and Limitations of Random Features for Understanding Neural Networks","created":"2019-04-01","cited_by_count":103},{"id":"2503.21878","title":"Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment","created":"2025-03-27","cited_by_count":97},{"id":"2401.00243","title":"Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles","created":"2023-12-30","cited_by_count":56},{"id":"2407.06057","title":"Variational Best-of-N Alignment","created":"2024-07-08","cited_by_count":51},{"id":"2301.13616","title":"Anti-Exploration by Random Network Distillation","created":"2023-01-31","cited_by_count":50},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50},{"id":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44},{"id":"2502.12668","title":"Evaluation of Best-of-N Sampling Strategies for Language Model Alignment","created":"2025-02-18","cited_by_count":39},{"id":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34},{"id":"2403.05171","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","created":"2024-03-08","cited_by_count":33},{"id":"2409.15360","title":"Reward-Robust RLHF in LLMs","created":"2024-09-18","cited_by_count":32},{"id":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28},{"id":"2504.10337","title":"Heimdall: test-time scaling on the generative verification","created":"2025-04-14","cited_by_count":26},{"id":"2404.01054","title":"Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment","created":"2024-04-01","cited_by_count":25},{"id":"2210.06692","title":"Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief","created":"2022-10-13","cited_by_count":22},{"id":"2412.15118","title":"Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation","created":"2024-12-19","cited_by_count":21},{"id":"2504.06141","title":"Adversarial Training of Reward Models","created":"2025-04-08","cited_by_count":18},{"id":"2501.11463","title":"Curiosity-Driven Reinforcement Learning from Human Feedback","created":"2025-01-20","cited_by_count":15},{"id":"2302.04658","title":"The Sample Complexity of Approximate Rejection Sampling with Applications to Smoothed Online Learning","created":"2023-02-09","cited_by_count":13},{"id":"2303.00783","title":"Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces","created":"2023-03-01","cited_by_count":8},{"id":"2404.06003","title":"FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models","created":"2024-04-09","cited_by_count":7},{"id":"2410.20187","title":"Uncertainty-Penalized Direct Preference Optimization","created":"2024-10-26","cited_by_count":6},{"id":"1910.10840","title":"Attention-based Curiosity-driven Exploration in Deep Reinforcement Learning","created":"2019-10-23","cited_by_count":5},{"id":"2412.20834","title":"Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment","created":"2024-12-30","cited_by_count":4},{"id":"2110.13229","title":"Distributionally Robust Recurrent Decoders with Random Network Distillation","created":"2021-10-25","cited_by_count":2},{"id":"2302.10825","title":"Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning","created":"2023-02-21","cited_by_count":1}],"next_cursor":null}