{"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/is-attention-interpretable","title":"Is Attention Interpretable?","arxiv_id":"1906.03731","date":"2019-06-09","proceeding":"ACL 2019 7","authors":["Sofia Serrano","Noah A. Smith"],"abstract":"Attention mechanisms have recently boosted performance on a range of NLP tasks. Because attention layers explicitly weight input components' representations, it is also often assumed that attention can be used to identify information that models found important (e.g., specific contextualized word tokens). We test whether that assumption holds by manipulating attention weights in already-trained text classification models and analyzing the resulting differences in their predictions. While we observe some ways in which higher attention weights correlate with greater impact on model predictions, we also find many ways in which this does not hold, i.e., where gradient-based rankings of attention weights better predict their effects than their magnitudes. We conclude that while attention noisily predicts input components' overall importance to a model, it is by no means a fail-safe indicator.","url_abs":"https://arxiv.org/abs/1906.03731v1","url_pdf":"https://arxiv.org/pdf/1906.03731v1.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":"is-attention-interpretable","repo_url":"https://github.com/serrano-s/attn-tests","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.03731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.03731"}},"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/serrano-s/attn-tests","reach":null}],"summary":{"ran_honours":1,"ran_fixture":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"53969a1f70369afe","entry":"get_test_accuracy","repo":"serrano-s/attn-tests","repo_kind":"official","path":"process_test_outputs.py","file_url":"https://github.com/serrano-s/attn-tests/blob/HEAD/process_test_outputs.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"53969a1f70369afe"}},{"code_sha256_prefix":"243868b74e3e051e","entry":"run_mcnemars_test","repo":"serrano-s/attn-tests","repo_kind":"official","path":"process_test_outputs.py","file_url":"https://github.com/serrano-s/attn-tests/blob/HEAD/process_test_outputs.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"243868b74e3e051e"}},{"code_sha256_prefix":"ca1f6f71977fb9fe","entry":"transfer_prev_model_weights_to_new_model","repo":"serrano-s/attn-tests","repo_kind":"official","path":"train_model.py","file_url":"https://github.com/serrano-s/attn-tests/blob/HEAD/train_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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ca1f6f71977fb9fe"}},{"code_sha256_prefix":"6e1e56afb631bcbe","entry":"load_in_data_table","repo":"serrano-s/attn-tests","repo_kind":"official","path":"process_test_outputs.py","file_url":"https://github.com/serrano-s/attn-tests/blob/HEAD/process_test_outputs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6e1e56afb631bcbe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}