{"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/quantifying-explainability-in-nlp-and","title":"Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff","arxiv_id":"2107.05693","date":"2021-07-12","proceeding":null,"authors":["Mitchell Naylor","Christi French","Samantha Terker","Uday Kamath"],"abstract":"The healthcare domain is one of the most exciting application areas for machine learning, but a lack of model transparency contributes to a lag in adoption within the industry. In this work, we explore the current art of explainability and interpretability within a case study in clinical text classification, using a task of mortality prediction within MIMIC-III clinical notes. We demonstrate various visualization techniques for fully interpretable methods as well as model-agnostic post hoc attributions, and we provide a generalized method for evaluating the quality of explanations using infidelity and local Lipschitz across model types from logistic regression to BERT variants. With these metrics, we introduce a framework through which practitioners and researchers can assess the frontier between a model's predictive performance and the quality of its available explanations. We make our code available to encourage continued refinement of these methods.","url_abs":"https://arxiv.org/abs/2107.05693v1","url_pdf":"https://arxiv.org/pdf/2107.05693v1.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":"quantifying-explainability-in-nlp-and","repo_url":"https://github.com/mnaylor5/quantifying-explainability","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"mortality-prediction","task_name":"Mortality Prediction"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"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":"lime","method_name":"LIME"},{"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":"logistic-regression","method_name":"Logistic Regression"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"shap","method_name":"SHAP"},{"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=2107.05693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05693"}},"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/mnaylor5/quantifying-explainability","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"ad8a7a7b81df1344","entry":"construct_embedding_distance_matrix","repo":"mnaylor5/quantifying-explainability","repo_kind":"official","path":"input_perturbation.py","file_url":"https://github.com/mnaylor5/quantifying-explainability/blob/HEAD/input_perturbation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ad8a7a7b81df1344"}},{"code_sha256_prefix":"75f83ed71c69939d","entry":"perturb_input_ids_torch","repo":"mnaylor5/quantifying-explainability","repo_kind":"official","path":"input_perturbation.py","file_url":"https://github.com/mnaylor5/quantifying-explainability/blob/HEAD/input_perturbation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"75f83ed71c69939d"}},{"code_sha256_prefix":"8c5ddf56921be517","entry":"perturb_input_ids_torch","repo":"mnaylor5/quantifying-explainability","repo_kind":"official","path":"input_perturbation.py","file_url":"https://github.com/mnaylor5/quantifying-explainability/blob/HEAD/input_perturbation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8c5ddf56921be517"}},{"code_sha256_prefix":"d0de3570857b14f4","entry":"sample_closest_words_transformer","repo":"mnaylor5/quantifying-explainability","repo_kind":"official","path":"input_perturbation.py","file_url":"https://github.com/mnaylor5/quantifying-explainability/blob/HEAD/input_perturbation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d0de3570857b14f4"}},{"code_sha256_prefix":"09cae7c395636577","entry":"sample_closest_words_transformer","repo":"mnaylor5/quantifying-explainability","repo_kind":"official","path":"input_perturbation.py","file_url":"https://github.com/mnaylor5/quantifying-explainability/blob/HEAD/input_perturbation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"09cae7c395636577"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}