cs.AI updates on arXiv.org 15小时前
Tracing Facts or just Copies? A critical investigation of the Competitions of Mechanisms in Large Language Models
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文研究了大型语言模型(LLMs)如何处理事实与反事实信息,重点关注注意力头在此过程中的作用。通过重现和调和现有研究,发现注意力头促进事实输出的机制和模式,并揭示了其领域依赖性。

arXiv:2507.11809v1 Announce Type: cross Abstract: This paper presents a reproducibility study examining how Large Language Models (LLMs) manage competing factual and counterfactual information, focusing on the role of attention heads in this process. We attempt to reproduce and reconcile findings from three recent studies by Ortu et al., Yu, Merullo, and Pavlick and McDougall et al. that investigate the competition between model-learned facts and contradictory context information through Mechanistic Interpretability tools. Our study specifically examines the relationship between attention head strength and factual output ratios, evaluates competing hypotheses about attention heads' suppression mechanisms, and investigates the domain specificity of these attention patterns. Our findings suggest that attention heads promoting factual output do so via general copy suppression rather than selective counterfactual suppression, as strengthening them can also inhibit correct facts. Additionally, we show that attention head behavior is domain-dependent, with larger models exhibiting more specialized and category-sensitive patterns.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

大型语言模型 事实与反事实信息 注意力头 机制解释
相关文章