{"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/the-mythos-of-model-interpretability","title":"The Mythos of Model Interpretability","arxiv_id":"1606.03490","date":"2016-06-10","proceeding":null,"authors":["Zachary C. Lipton"],"abstract":"Supervised machine learning models boast remarkable predictive capabilities.\nBut can you trust your model? Will it work in deployment? What else can it tell\nyou about the world? We want models to be not only good, but interpretable. And\nyet the task of interpretation appears underspecified. Papers provide diverse\nand sometimes non-overlapping motivations for interpretability, and offer\nmyriad notions of what attributes render models interpretable. Despite this\nambiguity, many papers proclaim interpretability axiomatically, absent further\nexplanation. In this paper, we seek to refine the discourse on\ninterpretability. First, we examine the motivations underlying interest in\ninterpretability, finding them to be diverse and occasionally discordant. Then,\nwe address model properties and techniques thought to confer interpretability,\nidentifying transparency to humans and post-hoc explanations as competing\nnotions. Throughout, we discuss the feasibility and desirability of different\nnotions, and question the oft-made assertions that linear models are\ninterpretable and that deep neural networks are not.","url_abs":"http://arxiv.org/abs/1606.03490v3","url_pdf":"http://arxiv.org/pdf/1606.03490v3.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":"the-mythos-of-model-interpretability","repo_url":"https://github.com/cmougan/WRI_WellBeing_Data_Layer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"the-mythos-of-model-interpretability","repo_url":"https://github.com/dssg/solveforgood-wri","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1606.03490","atlas_url":"https://app.syntology.ai/?focus=1606.03490","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}