English(EN) Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models

新的CREDIT方法提高了语言模型的自我归因能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

一篇新论文介绍了一种名为CREDIT的方法，旨在提高语言模型的自我归因能力，使其能够更好地表明其答案是否受到提供信息的影响。研究发现，大多数前沿模型在准确归因方面存在困难，常常未能承认有影响力的信息或错误地归因于无影响力的数据。CREDIT采用反事实训练和对最终答案归因的直接监督（无需人工标注），显著提高了开源模型的自我归因能力，并且优于现有的微调和提示技术。 AI

影响增强了语言模型的透明度和可问责性，可能提高用户信任度和AI生成信息的可靠性。

排序理由该集群是关于一篇详细介绍改进语言模型新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群是关于一篇详细介绍改进语言模型新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Zikai Zhou, Jiacheng Sang, Yilin Xu, Yufei Jin, Monica S. Lam · 2026-10-27 04:00

模型使用了那个吗？反事实训练提高了语言模型的自我归因能力

arXiv:2610.35295v1 Announce Type: cross 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 -…

本文如何被排名

报道来源 [1]

模型使用了那个吗？反事实训练提高了语言模型的自我归因能力

相关实体

相关话题