语言模型中社会政治框架的机制可解释性
Mechanistic Interpretability of Socio-Political Frames in Language Models
AI总结：
该研究聚焦大语言模型的社会政治认知框架生成与识别能力，通过机制可解释性方法定位“严父”“慈亲”框架对应的模型隐藏表征维度，为理解大语言模型的人类概念捕捉机制提供了新依据。
摘要：
本文探讨了大语言模型在社会政治语境下生成与识别深层认知框架的能力。我们证明，大语言模型在生成唤起特定框架的文本方面表现出极高的流畅度，且能在零样本设置下识别这些框架。受机制可解释性研究启发，我们探究了“严父”和“慈亲”框架在模型隐藏表征中的位置，识别出与二者存在强相关性的单一维度。本研究发现有助于理解大语言模型如何捕捉和表达有意义的人类概念。
英文摘要：
This paper explores the ability of large language models to generate and recognize deep cognitive frames, particularly in socio-political contexts. We demonstrate that LLMs are highly fluent in generating texts that evoke specific frames and can recognize these frames in zero-shot settings. Inspired by mechanistic interpretability research, we investigate the location of the `strict father' and `nurturing parent' frames within the model's hidden representation, identifying singular dimensions that correlate strongly with their presence. Our findings contribute to understanding how LLMs capture and express meaningful human concepts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
