研究:專家異議下,LLM 改答未必提升準確率
When Expert Disagreement Hurts: Prestige and Selectivity in LLM Decision Revision
這項研究以受控的兩輪審核測試語言模型在不同異議情境下如何修訂決策,發現模型在專家異議下往往未能有選擇地糾正錯誤,準確率最多下降 16.1 個百分點。研究涵蓋 5 個模型及醫學、科學和法律領域的 1,989 項有證據依據的決策;專家標籤令 5 個模型中的 4 個更常改答,但對準確率的影響介乎下降 5.2 個百分點至上升 2.4 個百分點。研究建議按模型和測試方案,使用成對的條件指標評估修訂流程。
Published on Nov 12
Authors:
Abstract
A controlled two-pass audit varying only the revision context reveals that language models often fail to selectively correct errors under disagreement, with expert labels increasing reversals but not reliably improving accuracy, so revision should be assessed using paired conditional metrics per model and protocol.
When language models revise a decision after another agent disagrees, neither reversal counts nor final accuracy shows whether they are fixing mistakes or abandoning correct answers. We introduce a controlled two-pass audit that holds the question, the evidence, and the model's initial answer fixed and varies only the revision context: neutral reflection, anonymous disagreement, or disagreement attributed to a domain expert. For binary decisions the accounting is exact: revision raises accuracy only if it is selective enough, reversing wrong answers more than a/(1-a) times as often as correct ones, where a is initial accuracy (nine times at 90%). Across five models and 1,989 evidence-grounded decisions in medicine, science, and law, no model clears this bar under expert disagreement, and accuracy falls by up to 16.1 points. The expert label, a prestige cue, adds reversals for four of the five models, yet its effect on accuracy ranges from a 5.2-point loss to a 2.4-point gain, so reversal counts are a poor proxy for harm. With identical arguments from both sources, the label still raises reversal for three proprietary models and in a pooled analysis of four newer models. Models also respond to stated source reliability. Revision pipelines should therefore be evaluated with paired, conditional metrics, per model and protocol.
View arXiv page View PDF Project page GitHub 3 Add to collection
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.16694 in a model README.md to link it from this page.
Datasets citing this paper 1
yupengtang/when-expert-disagreement-hurts
Viewer • Updated 4 days ago • 32.3k • 91
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.16694 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co