語言模型有否使用外部資訊?CREDIT 反事實訓練提升自我歸因能力
Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models
CREDIT 透過反事實訓練改善語言模型對外部資訊的自我歸因,減少模型錯誤承認未影響答案的資訊來源。該方法以反事實標籤直接監督最終答案,無需人工標註,並在四個開源模型(包括兩個蒸餾推理模型)上提升歸因表現,優於推理層微調及提示詞基線。提升效果亦部分泛化至未見資訊類型,以及包含支持相互矛盾答案來源的提示詞。
Published on Oct 26
Authors:
,
,
Abstract
CREDIT improves language model self-attribution of external information via counterfactual training, reducing false acknowledgment of non-influential sources.
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.
View arXiv page View PDF GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.35295
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.35295 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.35295 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.35295 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