adversarial-llm-judge

【数据与研究】Uncover and fix reward hacking vulnerabilities in LLM-based judges. Simple tokens like punctuation or generic reasoning phrases trigger false positive rewards without substantive content. Defend using data augmentation with truncated model outputs as adversarial negatives, creating robust Master Reward Models resistant to superficial inputs.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准