Papers with reward hacking problem
Weights-Rotated Preference Optimization for Large Language Models (2025.emnlp-main)
Copied to clipboard
Chenxu Yang, Ruipeng Jia, Mingyu Zheng, Naibin Gu, Zheng Lin, Siyuan Chen, Weichong Yin, Hua Wu, Weiping Wang
| Challenge: | Existing methods to align large language models with high reward hacking are limited by the complexity of the parameter space and the complexity. |
| Approach: | They propose a weights-rotated preference optimization algorithm that constrains the output layer logits with the KL divergence inherited from DPO and fine-tunes the intermediate hidden states. |
| Outcome: | The proposed algorithm achieves a 3.27-point improvement on AlpacaEval 2 and surpasses the best baseline by 6.2 to 7.5 points on MT-Bench with merely 0.015% of the trainable parameters. |
Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning (2026.acl-long)
Copied to clipboard
Siyuan Gan, Jiaheng Liu, Boyan Wang, Tianpei Yang, Runqing Miao, Yuyao Zhang, Fanyu Meng, Junlan Feng, Linjian Meng, Jing Huo, Yang Gao
| Challenge: | Existing work on large reasoning models (LRMs) focuses on using reinforcement learning (RL) to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query. |
| Approach: | They propose to use reinforcement learning to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query. |
| Outcome: | The proposed model reduces token usage by around 50%$ compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5b, while significantly improving accuracy. |