{"ID":2837224,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.20910","arxiv_id":"2511.20910","title":"Emergence and Localisation of Semantic Role Circuits in LLMs","abstract":"Despite displaying semantic competence, large language models' internal mechanisms that ground abstract semantic structure remain insufficiently characterised. We propose a method integrating role-cross minimal pairs, temporal emergence analysis, and cross-model comparison to study how LLMs implement semantic roles. Our analysis uncovers: (i) highly concentrated circuits (89-94% attribution within 28 nodes); (ii) gradual structural refinement rather than phase transitions, with larger models sometimes bypassing localised circuits; and (iii) moderate cross-scale conservation (24-59% component overlap) alongside high spectral similarity. These findings suggest that LLMs form compact, causally isolated mechanisms for abstract semantic structure, and these mechanisms exhibit partial transfer across scales and architectures.","short_abstract":"Despite displaying semantic competence, large language models' internal mechanisms that ground abstract semantic structure remain insufficiently characterised. We propose a method integrating role-cross minimal pairs, temporal emergence analysis, and cross-model comparison to study how LLMs implement semantic roles. Ou...","url_abs":"https://arxiv.org/abs/2511.20910","url_pdf":"https://arxiv.org/pdf/2511.20910v2","authors":"[\"Nura Aljaafari\",\"Danilo S. Carvalho\",\"André Freitas\"]","published":"2025-11-25T22:51:34Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}