기본 LLM의 잠재된 자체 평가 능력 추출, 최소 데이터로 가능
Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data
- 매체
- Hugging Face
- 게시
- 중요도
- 3/5
- 화제 지수
- 3
한국어 요약
연구팀이 기본 LLM이 외부 판정자의 평가를 예측하는 능력을 이미 보유하고 있음을 발견했다. Self-Evaluation Elicitation(SEE) 방법을 통해 160개 예제만으로 강화학습 기준 대비 31배 적은 데이터로 자체 평가 능력을 향상시킬 수 있음을 보였다. 이는 자체 평가를 새로운 능력 습득이 아닌 기존 능력의 추출 문제로 재정의한다.
원문 발췌 · English
Large language models are increasingly evaluated by other models, raising a natural question: can a model predict how a judge will score its own output? We find that the ability is largely present before any targeted training: prompted few-shot, a base model already predicts an external judge's multi-attribute quality scores on open-ended responses well above chance across three benchmarks. We introduce Self-Evaluation Elicitation (SEE), a method that surfaces this latent ability through a short cycle comprising a calibration-coupled reinforcement learning phase that improves the answer and predicts the judge, followed by a masked distillation phase that sharpens the prediction while leaving the answer untouched. From 160 unique examples, roughly 31x fewer than a reinforcement learning baseline, SEE improves held-out calibration across three benchmarks while preserving answer quality. The elicited self-evaluation is sharply localized within the model's own token distribution and stable across judges it was never trained against, indicating a transferable notion of quality rather than a single judge's preference. These results reframe judge-aligned self-evaluation as a problem of elicitation rather than acquisition.