Different types of syntactic agreement recruit the same units within large language models

TL;DR

This study reveals that large language models use overlapping units to process various types of syntactic agreement across multiple languages, indicating a shared representational basis.

Contribution

It demonstrates that different syntactic agreement phenomena recruit shared units in LLMs, highlighting a unified representational structure for agreement.

Findings

Shared units are recruited across different agreement types.

Agreement units are consistent across languages.

Structurally similar languages share more units for agreement.

Abstract

Large language models (LLMs) can reliably distinguish grammatical from ungrammatical sentences, but how grammatical knowledge is represented within the models remains an open question. We investigate whether different syntactic phenomena recruit shared or distinct components in LLMs. Using a functional localization approach inspired by cognitive neuroscience, we identify the LLM units most responsive to 67 English syntactic phenomena in seven open-weight models. These units are consistently recruited across sentences containing the phenomena and causally support the models' syntactic performance. Critically, different types of syntactic agreement (e.g., subject-verb, anaphor, determiner-noun) recruit overlapping sets of units, suggesting that agreement constitutes a meaningful functional category for LLMs. This pattern holds in English, Russian, and Chinese; and further, in a cross-lingual analysis of 57 diverse languages, structurally more similar languages share more units for subject-verb agreement. Taken together, these findings reveal that syntactic agreement-a critical marker of syntactic dependencies-constitutes a meaningful category within LLMs' representational spaces.