Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models
Targeted syntactic evaluations have demonstrated the ability of language models to perform subject-verb agreement given difficult contexts. To elucidate the mechanisms by which the models accomplish this behavior, this study applies causal mediation analysis to pre-trained neural language models. We investigate the magnitude of models' preferences for grammatical inflections, as well as whether neurons process subject-verb agreement similarly across sentences with different syntactic structures. We uncover similarities and differences across architectures and model sizes -- notably, that larger models do not necessarily learn stronger preferences. We also observe two distinct mechanisms for producing subject-verb agreement depending on the syntactic structure of the input sentence. Finally, we find that language models rely on similar sets of neurons when given sentences with similar syntactic structure.
Code (1)
Tasks
SentenceSimilar Papers 제목 키워드 기반
Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models
Structural probing work has found evidence for latent syntactic information in pre-trained language models. However, much of this analysis has focused on monolingual models, and analyses of multilingual models have emplo…
counterfactualShared Circuits for Shared Grammar: Tracing Subject-Verb Agreement Across Languages
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…
Different types of syntactic agreement recruit the same units within large language models
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 sy…
Assessing the Capacity of Transformer to Abstract Syntactic Representations: A Contrastive Analysis Based on Long-distance Agreement
The long-distance agreement, evidence for syntactic structure, is increasingly used to assess the syntactic generalization of Neural Language Models. Much work has shown that transformers are capable of high accuracy in …
counterfactualObjectHow Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement Tasks
This work addresses the question of the localization of syntactic information encoded in the transformers representations. We tackle this question from two perspectives, considering the object-past participle agreement i…
feature selectionSentence