Saved in:
Bibliographic Details
Main Authors: Aljaafari, Nura, Carvalho, Danilo S., Freitas, André
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.20910
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914234718224384
author Aljaafari, Nura
Carvalho, Danilo S.
Freitas, André
author_facet Aljaafari, Nura
Carvalho, Danilo S.
Freitas, André
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20910
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Emergence and Localisation of Semantic Role Circuits in LLMs
Aljaafari, Nura
Carvalho, Danilo S.
Freitas, André
Computation and Language
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.
title Emergence and Localisation of Semantic Role Circuits in LLMs
topic Computation and Language
url https://arxiv.org/abs/2511.20910