{"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/do-feature-attribution-methods-correctly","title":"Do Feature Attribution Methods Correctly Attribute Features?","arxiv_id":"2104.14403","date":"2021-04-27","proceeding":null,"authors":["Yilun Zhou","Serena Booth","Marco Tulio Ribeiro","Julie Shah"],"abstract":"Feature attribution methods are exceedingly popular in interpretable machine learning. They aim to compute the attribution of each input feature to represent its importance, but there is no consensus on the definition of \"attribution\", leading to many competing methods with little systematic evaluation. The lack of attribution ground truth further complicates evaluation, which has to rely on proxy metrics. To address this, we propose a dataset modification procedure such that models trained on the new dataset have ground truth attribution available. We evaluate three methods: saliency maps, rationales, and attention. We identify their deficiencies and add a new perspective to the growing body of evidence questioning their correctness and reliability in the wild. Our evaluation approach is model-agnostic and can be used to assess future feature attribution method proposals as well. Code is available at https://github.com/YilunZhou/feature-attribution-evaluation.","url_abs":"https://arxiv.org/abs/2104.14403v1","url_pdf":"https://arxiv.org/pdf/2104.14403v1.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":"do-feature-attribution-methods-correctly","repo_url":"https://github.com/YilunZhou/feature-attribution-evaluation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"interpretable-machine-learning","task_name":"Interpretable Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.14403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.14403"}},"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/YilunZhou/feature-attribution-evaluation","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"d9277bbec1029b13","entry":"custom_collate_fn","repo":"YilunZhou/feature-attribution-evaluation","repo_kind":"official","path":"text_rationale_attention/attention_model.py","file_url":"https://github.com/YilunZhou/feature-attribution-evaluation/blob/HEAD/text_rationale_attention/attention_model.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":"d9277bbec1029b13"}},{"code_sha256_prefix":"11d8c820078320f3","entry":"evaluate","repo":"YilunZhou/feature-attribution-evaluation","repo_kind":"official","path":"text_rationale_attention/attention_model.py","file_url":"https://github.com/YilunZhou/feature-attribution-evaluation/blob/HEAD/text_rationale_attention/attention_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"11d8c820078320f3"}},{"code_sha256_prefix":"79d2a0642224e83f","entry":"masked_softmax","repo":"YilunZhou/feature-attribution-evaluation","repo_kind":"official","path":"text_rationale_attention/attention_model.py","file_url":"https://github.com/YilunZhou/feature-attribution-evaluation/blob/HEAD/text_rationale_attention/attention_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"79d2a0642224e83f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}