{"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/local-rule-based-explanations-of-black-box","title":"Local Rule-Based Explanations of Black Box Decision Systems","arxiv_id":"1805.10820","date":"2018-05-28","proceeding":null,"authors":["Riccardo Guidotti","Anna Monreale","Salvatore Ruggieri","Dino Pedreschi","Franco Turini","Fosca Giannotti"],"abstract":"The recent years have witnessed the rise of accurate but obscure decision\nsystems which hide the logic of their internal decision processes to the users.\nThe lack of explanations for the decisions of black box systems is a key\nethical issue, and a limitation to the adoption of machine learning components\nin socially sensitive and safety-critical contexts. %Therefore, we need\nexplanations that reveals the reasons why a predictor takes a certain decision.\nIn this paper we focus on the problem of black box outcome explanation, i.e.,\nexplaining the reasons of the decision taken on a specific instance. We propose\nLORE, an agnostic method able to provide interpretable and faithful\nexplanations. LORE first leans a local interpretable predictor on a synthetic\nneighborhood generated by a genetic algorithm. Then it derives from the logic\nof the local interpretable predictor a meaningful explanation consisting of: a\ndecision rule, which explains the reasons of the decision; and a set of\ncounterfactual rules, suggesting the changes in the instance's features that\nlead to a different outcome. Wide experiments show that LORE outperforms\nexisting methods and baselines both in the quality of explanations and in the\naccuracy in mimicking the black box.","url_abs":"http://arxiv.org/abs/1805.10820v1","url_pdf":"http://arxiv.org/pdf/1805.10820v1.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":"local-rule-based-explanations-of-black-box","repo_url":"https://github.com/anahid1988/DeepRUL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.10820","atlas_url":"https://app.syntology.ai/?focus=1805.10820","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}