Skip to content
conftrace_

reward overoptimization

9 papers

Explore in graph

Co-occurring keywords · papers mentioning both

reward model (5) reinforcement learning from human feedback (5) large language model (4) reinforcement learning (3) language model alignment (2) preference learning (2) human alignment (1) report generation (1) primacy bia (1) gradient reweighting (1)

Papers

GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping CVPR 2026 PIRA: Preference-Oriented Instruction-Tuned Reward Models with Dual Aggregation EACL 2026 CheXalign: Preference fine-tuning in chest X-ray interpretation models without human feedback ACL 2025 Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization ACL 2025 Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases ICML 2024 Countering Reward Over-Optimization in LLM with Demonstration-Guided Reinforcement Learning ACL 2024 InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling NeurIPS 2024 Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation NeurIPS 2024 Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs NeurIPS 2024