{"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/what-bert-is-not-lessons-from-a-new-suite-of","title":"What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models","arxiv_id":"1907.13528","date":"2019-07-31","proceeding":"TACL 2020 1","authors":["Allyson Ettinger"],"abstract":"Pre-training by language modeling has become a popular and successful approach to NLP tasks, but we have yet to understand exactly what linguistic capacities these pre-training processes confer upon models. In this paper we introduce a suite of diagnostics drawn from human language experiments, which allow us to ask targeted questions about the information used by language models for generating predictions in context. As a case study, we apply these diagnostics to the popular BERT model, finding that it can generally distinguish good from bad completions involving shared category or role reversal, albeit with less sensitivity than humans, and it robustly retrieves noun hypernyms, but it struggles with challenging inferences and role-based event prediction -- and in particular, it shows clear insensitivity to the contextual impacts of negation.","url_abs":"https://arxiv.org/abs/1907.13528v2","url_pdf":"https://arxiv.org/pdf/1907.13528v2.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":"what-bert-is-not-lessons-from-a-new-suite-of","repo_url":"https://github.com/aetting/lm-diagnostics","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"what-bert-is-not-lessons-from-a-new-suite-of","repo_url":"https://github.com/text-machine-lab/extending_psycholinguistic_dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"negation","task_name":"Negation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1907.13528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.13528"}},"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/text-machine-lab/extending_psycholinguistic_dataset","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aetting/lm-diagnostics","reach":null}],"summary":{"ran_draft_wrong":5,"unverified":5},"by_repo_kind":{"official":{"samples":9,"ran":4,"repositories":1},"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"c7ea9c0d23888444","entry":"convert_to_experiment_grouping","repo":"aetting/lm-diagnostics","repo_kind":"official","path":"sensitivity_tests.py","file_url":"https://github.com/aetting/lm-diagnostics/blob/HEAD/sensitivity_tests.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c7ea9c0d23888444"}},{"code_sha256_prefix":"1049fad948492b30","entry":"process_data","repo":"text-machine-lab/extending_psycholinguistic_dataset","repo_kind":"listed","path":"src/evaluation.py","file_url":"https://github.com/text-machine-lab/extending_psycholinguistic_dataset/blob/HEAD/src/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1049fad948492b30"}},{"code_sha256_prefix":"fbc8f579aac35580","entry":"process_fischler","repo":"aetting/lm-diagnostics","repo_kind":"official","path":"run_diagnostics_bert.py","file_url":"https://github.com/aetting/lm-diagnostics/blob/HEAD/run_diagnostics_bert.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbc8f579aac35580"}},{"code_sha256_prefix":"ea717e639e6df8cf","entry":"process_fk","repo":"aetting/lm-diagnostics","repo_kind":"official","path":"run_diagnostics_bert.py","file_url":"https://github.com/aetting/lm-diagnostics/blob/HEAD/run_diagnostics_bert.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea717e639e6df8cf"}},{"code_sha256_prefix":"91c10b6209d86836","entry":"process_rr","repo":"aetting/lm-diagnostics","repo_kind":"official","path":"run_diagnostics_bert.py","file_url":"https://github.com/aetting/lm-diagnostics/blob/HEAD/run_diagnostics_bert.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"91c10b6209d86836"}},{"code_sha256_prefix":"d9cd894ddd324224","entry":"cprag_sensitivity_test","repo":"aetting/lm-diagnostics","repo_kind":"official","path":"sensitivity_tests.py","file_url":"https://github.com/aetting/lm-diagnostics/blob/HEAD/sensitivity_tests.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":"d9cd894ddd324224"}},{"code_sha256_prefix":"ac1c3b07a675902f","entry":"role_sensitivity_test","repo":"aetting/lm-diagnostics","repo_kind":"official","path":"sensitivity_tests.py","file_url":"https://github.com/aetting/lm-diagnostics/blob/HEAD/sensitivity_tests.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":"ac1c3b07a675902f"}},{"code_sha256_prefix":"bc23445d491b4ec9","entry":"test_cprag_acc","repo":"aetting/lm-diagnostics","repo_kind":"official","path":"prediction_accuracy_tests.py","file_url":"https://github.com/aetting/lm-diagnostics/blob/HEAD/prediction_accuracy_tests.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":"bc23445d491b4ec9"}},{"code_sha256_prefix":"2af208405982a958","entry":"test_neg_acc","repo":"aetting/lm-diagnostics","repo_kind":"official","path":"prediction_accuracy_tests.py","file_url":"https://github.com/aetting/lm-diagnostics/blob/HEAD/prediction_accuracy_tests.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":"2af208405982a958"}},{"code_sha256_prefix":"d1163a4e501f8984","entry":"test_role_acc","repo":"aetting/lm-diagnostics","repo_kind":"official","path":"prediction_accuracy_tests.py","file_url":"https://github.com/aetting/lm-diagnostics/blob/HEAD/prediction_accuracy_tests.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":"d1163a4e501f8984"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}