{"list":"other","total":57,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"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":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"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":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"2410.18451","title":"Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs","created":"2024-10-24","cited_by_count":327},{"id":"2310.07641","title":"Evaluating Large Language Models at Evaluating Instruction Following","created":"2023-10-11","cited_by_count":302},{"id":"1711.02827","title":"Inverse Reward Design","created":"2017-11-08","cited_by_count":249},{"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":"2406.10162","title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","created":"2024-06-14","cited_by_count":178},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147},{"id":"2406.10216","title":"Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs","created":"2024-06-14","cited_by_count":142},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137},{"id":"2402.07319","title":"ODIN: Disentangled Reward Mitigates Hacking in RLHF","created":"2024-02-11","cited_by_count":136},{"id":"2310.17022","title":"Controlled Decoding from Language Models","created":"2023-10-25","cited_by_count":135},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126},{"id":"2401.01879","title":"Theoretical guarantees on the best-of-n alignment policy","created":"2024-01-03","cited_by_count":124},{"id":"2405.16436","title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer","created":"2024-05-26","cited_by_count":109},{"id":"2407.06551","title":"OffsetBias: Leveraging Debiased Data for Tuning Evaluators","created":"2024-07-09","cited_by_count":94},{"id":"2412.15287","title":"Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models","created":"2024-12-18","cited_by_count":89},{"id":"2410.14872","title":"How to Evaluate Reward Models for RLHF","created":"2024-10-18","cited_by_count":88},{"id":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79},{"id":"2402.06627","title":"Feedback Loops With Language Models Drive In-Context Reward Hacking","created":"2024-02-09","cited_by_count":77},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76},{"id":"2409.13156","title":"RRM: Robust Reward Model Training Mitigates Reward Hacking","created":"2024-09-20","cited_by_count":76},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57},{"id":"2502.13295","title":"Demonstrating specification gaming in reasoning models","created":"2025-02-18","cited_by_count":56},{"id":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50},{"id":"2501.09620","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","created":"2025-01-16","cited_by_count":42},{"id":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41},{"id":"2403.05171","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","created":"2024-03-08","cited_by_count":33},{"id":"2309.16155","title":"The Trickle-down Impact of Reward (In-)consistency on RLHF","created":"2023-09-28","cited_by_count":29},{"id":"2407.04549","title":"Spontaneous Reward Hacking in Iterative Self-Refinement","created":"2024-07-05","cited_by_count":26},{"id":"2407.14503","title":"Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification","created":"2024-07-19","cited_by_count":23},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20},{"id":"2501.19358","title":"The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking","created":"2025-01-31","cited_by_count":18},{"id":"2406.01013","title":"Scalable Ensembling For Mitigating Reward Overoptimisation","created":"2024-06-03","cited_by_count":14},{"id":"2412.09544","title":"Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking","created":"2024-12-12","cited_by_count":13},{"id":"2410.09638","title":"On Goodhart's law, with an application to value alignment","created":"2024-10-12","cited_by_count":9},{"id":"2503.06810","title":"Mitigating Preference Hacking in Policy Optimization with Pessimism","created":"2025-03-10","cited_by_count":8},{"id":"2406.15753","title":"The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret","created":"2024-06-22","cited_by_count":6},{"id":"2504.14838","title":"Establishing Reliability Metrics for Reward Models in Large Language Models","created":"2025-04-21","cited_by_count":1}],"next_cursor":null}