reward hacking

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning ACL 2026 TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles ACL 2026 Adversarial Preference Learning for Robust LLM Alignment ACL 2025 BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping ICLR 2025 CARMO: Dynamic Criteria Generation for Context Aware Reward Modelling ACL 2025 Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking ICLR 2025 Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models WACV 2025 Fixing Distribution Shifts of LLM Self-Critique via On-Policy Self-Play Training ACL 2025 Logical Reasoning with Outcome Reward Models for Test-Time Scaling EMNLP 2025 Position: AI Safety Must Embrace an Antifragile Perspective ICML 2025 Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment NAACL 2025 Removing Prompt-template Bias in Reinforcement Learning from Human Feedback ACL 2025 RRM: Robust Reward Model Training Mitigates Reward Hacking ICLR 2025 Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking ICLR 2025 The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking ICML 2025 Towards Federated RLHF with Aggregated Client Preference for LLMs ICLR 2025 Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL ACL 2025 Weights-Rotated Preference Optimization for Large Language Models EMNLP 2025 When Can Proxies Improve the Sample Complexity of Preference Learning? ICML 2025 Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification NeurIPS 2024 Improving Generalization of Alignment with Human Preferences through Group Invariant Learning ICLR 2024 InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling NeurIPS 2024 ODIN: Disentangled Reward Mitigates Hacking in RLHF ICML 2024 Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms NeurIPS 2024 The Alignment Problem from a Deep Learning Perspective ICLR 2024