{"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/evaluating-attribution-methods-using-white","title":"Evaluating Attribution Methods using White-Box LSTMs","arxiv_id":"2010.08606","date":"2020-10-16","proceeding":"EMNLP (BlackboxNLP) 2020 11","authors":["Yiding Hao"],"abstract":"Interpretability methods for neural networks are difficult to evaluate because we do not understand the black-box models typically used to test them. This paper proposes a framework in which interpretability methods are evaluated using manually constructed networks, which we call white-box networks, whose behavior is understood a priori. We evaluate five methods for producing attribution heatmaps by applying them to white-box LSTM classifiers for tasks based on formal languages. Although our white-box classifiers solve their tasks perfectly and transparently, we find that all five attribution methods fail to produce the expected model explanations.","url_abs":"https://arxiv.org/abs/2010.08606v1","url_pdf":"https://arxiv.org/pdf/2010.08606v1.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":"evaluating-attribution-methods-using-white","repo_url":"https://github.com/yidinghao/whitebox-lstm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.08606","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}