arXiv cs.CL· Zikai Zhou, Jiacheng Sang, Yilin Xu, Yufei Jin, Monica S. Lam·· 12 小时前AI 评分42
模型是否用了那条信息？反事实训练提升语言模型的自我归因能力
Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models
AI 导读
研究提出 CREDIT 方法，用反事实标签直接监督最终答案的自我归因，无需人工标注，在四个开源模型（含两个蒸馏推理模型）上显著提升归因表现，并优于推理层微调与提示词基线。
正文
Abstract:A fundamental challenge for explainable and accountable language models is revealing how external information influences their answers. This paper examines whether models are self-attributive: that is, whether they indicate when -- and only when -- their responses to questions are influenced by information provided alongside the question. Furthermore, we explore how self-attribution can be improved through counterfactual training, which explicitly teaches models to distinguish between answers that do and do not depend on supplied information.
We found that most of the eleven frontier models rarely attribute influential information in their answers, and the rest attribute non-influential information. Training acknowledgment into reasoning does not fix this: the acknowledgment does not reach the final answer.
We introduce CREDIT, which directly supervises final-answer self-attribution with counterfactual labels, without the need for human annotation. CREDIT substantially improves attribution in four open models, including two distilled reasoning models, and outperforms reasoning-level fine-tuning and prompting baselines. Among answers that agree with a user's suggestion, CREDIT distinguishes those changed by the suggestion from those the model would have given anyway. Gains transfer partly to unseen information types and prompts containing sources that support conflicting answers.
| Comments: | 29 pages, 5 figures, 20 tables. Code: this https URL |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.7 |
| Cite as: | arXiv:2610.35295 [cs.CL] |
| (or arXiv:2610.35295v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35295 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zikai Zhou [view email]
[v1]
Mon, 26 Oct 2026 12:03:05 UTC (222 KB)
来源：arXiv cs.CL · arxiv.org