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

arXiv:2512.03676v2 Announce Type: replace 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.

Related

• Psychological Concept Neurons: Can Neural Control Bias Probing and Shift Generation in LLMs?
• Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution
• Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation
• Why Code, Why Now: An Information-Theoretic Perspective on the Limits of Machine Learning

Source: arXiv cs.CL | 2026-04-14