{"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/beyond-accuracy-behavioral-testing-of-nlp","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","arxiv_id":"2005.04118","date":"2020-05-08","proceeding":"ACL 2020 6","authors":["Marco Tulio Ribeiro","Tongshuang Wu","Carlos Guestrin","Sameer Singh"],"abstract":"Although measuring held-out accuracy has been the primary approach to evaluate generalization, it often overestimates the performance of NLP models, while alternative approaches for evaluating models either focus on individual tasks or on specific behaviors. Inspired by principles of behavioral testing in software engineering, we introduce CheckList, a task-agnostic methodology for testing NLP models. CheckList includes a matrix of general linguistic capabilities and test types that facilitate comprehensive test ideation, as well as a software tool to generate a large and diverse number of test cases quickly. We illustrate the utility of CheckList with tests for three tasks, identifying critical failures in both commercial and state-of-art models. In a user study, a team responsible for a commercial sentiment analysis model found new and actionable bugs in an extensively tested model. In another user study, NLP practitioners with CheckList created twice as many tests, and found almost three times as many bugs as users without it.","url_abs":"https://arxiv.org/abs/2005.04118v1","url_pdf":"https://arxiv.org/pdf/2005.04118v1.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":"beyond-accuracy-behavioral-testing-of-nlp","repo_url":"https://github.com/marcotcr/checklist","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"beyond-accuracy-behavioral-testing-of-nlp","repo_url":"https://github.com/jacopotagliabue/dag-card-is-the-new-model-card","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"beyond-accuracy-behavioral-testing-of-nlp","repo_url":"https://github.com/nballier/IDEEL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"beyond-accuracy-behavioral-testing-of-nlp","repo_url":"https://github.com/ucinlp/bibere","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[{"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":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.04118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.04118"}},"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/jacopotagliabue/dag-card-is-the-new-model-card","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/marcotcr/checklist","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ucinlp/bibere","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nballier/IDEEL","reach":{"status":"ok"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"38fb77d998e2e875","entry":"clean_senses","repo":"marcotcr/checklist","repo_kind":"official","path":"checklist/text_generation.py","file_url":"https://github.com/marcotcr/checklist/blob/HEAD/checklist/text_generation.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":"38fb77d998e2e875"}},{"code_sha256_prefix":"1b86c6b7a8f3ceef","entry":"iter_with_optional","repo":"marcotcr/checklist","repo_kind":"official","path":"checklist/expect.py","file_url":"https://github.com/marcotcr/checklist/blob/HEAD/checklist/expect.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":"1b86c6b7a8f3ceef"}},{"code_sha256_prefix":"b01cb2044b6b11f9","entry":"process_ret","repo":"marcotcr/checklist","repo_kind":"official","path":"checklist/perturb.py","file_url":"https://github.com/marcotcr/checklist/blob/HEAD/checklist/perturb.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":"b01cb2044b6b11f9"}},{"code_sha256_prefix":"7119d0199094dd5f","entry":"recursive_apply","repo":"marcotcr/checklist","repo_kind":"official","path":"checklist/editor.py","file_url":"https://github.com/marcotcr/checklist/blob/HEAD/checklist/editor.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":"7119d0199094dd5f"}},{"code_sha256_prefix":"157c60c142af6297","entry":"recursive_format","repo":"marcotcr/checklist","repo_kind":"official","path":"checklist/editor.py","file_url":"https://github.com/marcotcr/checklist/blob/HEAD/checklist/editor.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":"157c60c142af6297"}},{"code_sha256_prefix":"43c9cb585e0725c1","entry":"replace_mask","repo":"marcotcr/checklist","repo_kind":"official","path":"checklist/editor.py","file_url":"https://github.com/marcotcr/checklist/blob/HEAD/checklist/editor.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":"43c9cb585e0725c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}