{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/causal-analysis-of-syntactic-agreement","title":"Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models","arxiv_id":"2106.06087","date":"2021-06-10","proceeding":"ACL 2021 5","authors":["Matthew Finlayson","Aaron Mueller","Sebastian Gehrmann","Stuart Shieber","Tal Linzen","Yonatan Belinkov"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2106.06087v3","url_pdf":"https://arxiv.org/pdf/2106.06087v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"causal-analysis-of-syntactic-agreement","repo_url":"https://github.com/mattf1n/lm-intervention","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2106.06087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06087"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mattf1n/lm-intervention","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8b82f9a93010e4f0","entry":"get_example_type","repo":"mattf1n/lm-intervention","repo_kind":"official","path":"analysis.py","file_url":"https://github.com/mattf1n/lm-intervention/blob/HEAD/analysis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8b82f9a93010e4f0"}},{"code_sha256_prefix":"f4f2de6acc87096f","entry":"get_odds_ratio","repo":"mattf1n/lm-intervention","repo_kind":"official","path":"attention_utils.py","file_url":"https://github.com/mattf1n/lm-intervention/blob/HEAD/attention_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f4f2de6acc87096f"}},{"code_sha256_prefix":"8b8f35543c6041ec","entry":"get_size","repo":"mattf1n/lm-intervention","repo_kind":"official","path":"analysis.py","file_url":"https://github.com/mattf1n/lm-intervention/blob/HEAD/analysis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8b8f35543c6041ec"}},{"code_sha256_prefix":"5c8ae037e542d8c4","entry":"perform_intervention","repo":"mattf1n/lm-intervention","repo_kind":"official","path":"attention_utils.py","file_url":"https://github.com/mattf1n/lm-intervention/blob/HEAD/attention_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c8ae037e542d8c4"}},{"code_sha256_prefix":"66d927a947f06f56","entry":"perform_interventions","repo":"mattf1n/lm-intervention","repo_kind":"official","path":"attention_utils.py","file_url":"https://github.com/mattf1n/lm-intervention/blob/HEAD/attention_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"66d927a947f06f56"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}