{"ID":2860579,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.03799","arxiv_id":"2510.03799","title":"Mechanistic Interpretability of Socio-Political Frames in Language Models","abstract":"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.","short_abstract":"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 inte...","url_abs":"https://arxiv.org/abs/2510.03799","url_pdf":"https://arxiv.org/pdf/2510.03799v1","authors":"[\"Hadi Asghari\",\"Sami Nenno\"]","published":"2025-10-04T12:39:39Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.CY\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}