English

Emergence and Localisation of Semantic Role Circuits in LLMs

Computation and Language 2026-01-07 v2

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.

Keywords

Cite

@article{arxiv.2511.20910,
  title  = {Emergence and Localisation of Semantic Role Circuits in LLMs},
  author = {Nura Aljaafari and Danilo S. Carvalho and André Freitas},
  journal= {arXiv preprint arXiv:2511.20910},
  year   = {2026}
}