{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/interpreting-neural-networks-with-nearest","title":"Interpreting Neural Networks With Nearest Neighbors","arxiv_id":"1809.02847","date":"2018-09-08","proceeding":"WS 2018 11","authors":["Eric Wallace","Shi Feng","Jordan Boyd-Graber"],"abstract":"Local model interpretation methods explain individual predictions by\nassigning an importance value to each input feature. This value is often\ndetermined by measuring the change in confidence when a feature is removed.\nHowever, the confidence of neural networks is not a robust measure of model\nuncertainty. This issue makes reliably judging the importance of the input\nfeatures difficult. We address this by changing the test-time behavior of\nneural networks using Deep k-Nearest Neighbors. Without harming text\nclassification accuracy, this algorithm provides a more robust uncertainty\nmetric which we use to generate feature importance values. The resulting\ninterpretations better align with human perception than baseline methods.\nFinally, we use our interpretation method to analyze model predictions on\ndataset annotation artifacts.","url_abs":"http://arxiv.org/abs/1809.02847v2","url_pdf":"http://arxiv.org/pdf/1809.02847v2.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":"interpreting-neural-networks-with-nearest","repo_url":"https://github.com/Eric-Wallace/trickme-interface","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"feature-importance","task_name":"Feature Importance"},{"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":{"syntology_url":"https://syntology.ai/paper/1809.02847","atlas_url":"https://app.syntology.ai/?focus=1809.02847","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1809.02847"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1809.02847\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1809.02847"},"call":"get_concepts_for_paper(arxiv_id=\"1809.02847\")"}],"by_repo":[{"repo":"Eric-Wallace/trickme-interface","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"835557ecad2119877c034d8df4bfd8dc229ee3d25d379b5acb7080fb35001aa4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}