3 papers
cs.LG2026
Beyond Semantic Manipulation: Token-Space Attacks on Reward Models
Yuheng Zhang, Mingyue Huo, Minghao Zhu +2
Reward models (RMs) are widely used as optimization targets in reinforcement learning from human feedback (RLHF), yet they remain vulnerable to reward hacking. Existing attacks mai…
eess.AS2025
Identifying and Calibrating Overconfidence in Noisy Speech Recognition
Mingyue Huo, Yuheng Zhang, Yan Tang
Modern end-to-end automatic speech recognition (ASR) models like Whisper not only suffer from reduced recognition accuracy in noise, but also exhibit overconfidence - assigning hig…
cs.LG2025
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
Yuheng Zhang, Dian Yu, Baolin Peng +6
Reinforcement Learning with Human Feedback (RLHF) has achieved great success in aligning large language models (LLMs) with human preferences. Prevalent RLHF approaches are reward-b…