arXiv:2611.04395 · v1

Correct Labels Are Not Enough: Reliable Metadata Can Silently Control Model Behavior

首次提交 2026-11-03 14:29

版本更新 2026-11-03 14:29

雷达观测 2026-11-04 23:40

摘要

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.

作者备注：NeurIPS 2026 AI4GOOD