arXiv cs.LG
Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
LLM 평가 중 내부 표현을 활용한 보상 해킹 모니터링 및 발견
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.