conftrace_

reward hacking

34 papers

Explore in graph

Co-occurring keywords

reinforcement learning (4352) reinforcement learning from human feedback (278) reward model (276) direct preference optimization (332) reward modeling (164) reward function (291) language model (4599) safe reinforcement learning (120) language model alignment (142) kl divergence (196)

Papers

Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction AAAI 2026
Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards ACL 2026
PRISM: Probabilistic Reward Model with Inherent Structural Modeling ACL 2026
Bias Fitting to Mitigate Length Bias of Reward Model in RLHF ACL 2026
Intrinsic Barriers and Practical Pathways for Human–AI Alignment: An Agreement-Based Complexity Analysis AAAI 2026
Specification-Guided Reinforcement Learning AAAI 2026
A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models AAAI 2026
A Reinforcement Learning Framework for Robust and Secure LLM Watermarking EACL 2026
ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models AAAI 2026
Multi-Metric Preference Alignment for Generative Speech Restoration AAAI 2026
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
PARIF: Pushing the Pareto Frontier of Instruction Following and Reasoning with Curriculum Reinforcement Learning ACL 2026
Adversarial Preference Learning for Robust LLM Alignment ACL 2025
Removing Prompt-template Bias in Reinforcement Learning from Human Feedback ACL 2025
CARMO: Dynamic Criteria Generation for Context Aware Reward Modelling ACL 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
Logical Reasoning with Outcome Reward Models for Test-Time Scaling EMNLP 2025
Fixing Distribution Shifts of LLM Self-Critique via On-Policy Self-Play Training ACL 2025
Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models WACV 2025
Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment NAACL 2025
Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification NIPS 2024
InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling NIPS 2024
Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms NIPS 2024