Different types of syntactic agreement recruit the same units within large language models
This provides insight into how LLMs represent grammatical knowledge, which is important for understanding model interpretability and linguistic theory, though it's incremental in building on existing localization approaches.
The researchers investigated how different types of syntactic agreement (e.g., subject-verb, anaphor, determiner-noun) are represented in large language models, finding that these phenomena recruit overlapping sets of units across 67 English syntactic phenomena in seven models, with the pattern holding in English, Russian, Chinese, and 57 diverse languages where structurally similar languages share more units for subject-verb agreement.
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.