Shared Circuits for Shared Grammar: Tracing Subject-Verb Agreement Across Languages

2026-08-19

AI Summary

研究通过激活修补和注意力分析，探讨了多语言大模型在处理主谓一致时的共享机制，发现有显性人称/数屈折变化的语言表现出更相似的处理电路。

Abstract

Multilingual large language models often generalize across languages, and prior work suggests that their internal mechanisms can overlap cross-lingually. It remains unclear, however, when such sharing emerges and whether it varies with the overt realization of the same grammatical operation. We investigate this question for present-tense subject-verb agreement, a morphosyntactic process that varies substantially across languages and is only weakly expressed in English. Using activation patching and attention analysis across 29 languages and five open-source model families, we identify the attention heads causally implicated in agreement and compare these head-level signatures across languages. We find that languages with overt person/number inflection exhibit more similar agreement circuitry than non-conjugating languages, with the strongest sharing appearing when the analysis isolates recovery of the inflectional contrast itself. English provides an informative bridge case, becoming more similar to conjugating languages precisely in contexts where overt agreement is required. Finally, many implicated heads display similar attention patterns across languages, suggesting that cross-lingual overlap reflects shared functional roles as well as shared localization. Together, these results indicate that multilingual LLMs reuse partially shared computational structure for morphosyntactic agreement rather than relying on fully separate language-specific solutions.

Problem

• multilingual large language models
• subject-verb agreement
• cross-lingual sharing
• morphosyntactic process
• internal mechanisms

Innovation

• multilingual large language models
• subject-verb agreement
• cross-lingual sharing
• activation patching
• attention analysis