arXiv q-bio + cs.AI: clinical/medical
Mitigating Reward Hacking in Preference Reward Models with Evolving Penalties
진화하는 벌칙을 활용한 선호 보상 모델에서의 보상 해킹 완화
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.