논문해외
All Quiet on the Neural Front: Language Models Do Not Report Injected Pain States
HF Daily Papers
Can a language model report the pain state it represents? Work identified a linear pain direction whose amplification leads fine-tuned models to choose destructive actions.
원문의 저작권은 HF Daily Papers에 있습니다. 위 발췌는 원문 확인을 돕기 위한 짧은 인용입니다.