Hugging Face Papers ↗ · 2026-11-03
Correct Labels Are Not Enough: Reliable Metadata Can Silently Control Model Behavior
研究论文 Hugging Face Papers 原文语言:中文
论文摘要(作者报告,未经本站复测):Fine-tuning data can include metadata that predicts the correct answer, such as a reward-model score or a quality label.
全文
Fine-tuning data can include metadata that predicts the correct answer, such as a reward-model score or a quality label. We ask whether a model learns to rely on this metadata even when every training label is correct. We fine-tune 7-9B open-weight models from three families on multiple-choice questions in which (Reward: 5) always marks the correct option; when this annotation is moved to a wrong option at test time, models select that option on 97-100% of CommonsenseQA items. Removing it leaves most answers correct, so evaluation without it misses the dependence. Cue-following rises sharply with training-time reliability and develops even with neutral or nonsense annotation words, although test-time wording affects its strength. A Qwen3 experiment also finds cue dependence in option-letter scores after direct preference optimization. Audits can test for this dependence by moving or removing visible annotations while holding the task and correct answer fixed.
View arXiv page View PDF Add to collection
正文以来源语言显示。