Dialogue Explanations for Rule-Based AI Systems. In Explainable and Transparent AI and Multi-Agent Systems, pages 59–77, Cham, 2023. Springer Nature Switzerland. [Computational Agent Responsibility]abstract bibtex The need for AI systems to explain themselves is increasingly recognised as a priority, particularly in domains where incorrect decisions can result in harm and, in the worst cases, death. Explainable Artificial Intelligence (XAI) tries to produce human-understandable explanations for AI decisions. However, most XAI systems prioritize factors such as technical complexities and research-oriented goals over end-user needs, risking information overload. This research attempts to bridge a gap in current understanding and provide insights for assisting users in comprehending the rule-based system's reasoning through dialogue. The hypothesis is that employing dialogue as a mechanism can be effective in constructing explanations. A dialogue framework for rule-based AI systems is presented, allowing the system to explain its decisions by engaging in ``Why?'' and ``Why not?'' questions and answers. We establish formal properties of this framework and present a small user study with encouraging results that compares dialogue-based explanations with proof trees produced by the AI System.
Downloads: 0
{"_id":"YnaXBuwRy7ZK9KTGp","bibbaseid":"anonymous-dialogueexplanationsforrulebasedaisystems-2023","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Xu"],"firstnames":["Yifan"],"suffixes":[]},{"propositions":[],"lastnames":["Collenette"],"firstnames":["Joe"],"suffixes":[]},{"propositions":[],"lastnames":["Dennis"],"firstnames":["Louise"],"suffixes":[]},{"propositions":[],"lastnames":["Dixon"],"firstnames":["Clare"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Calvaresi"],"firstnames":["Davide"],"suffixes":[]},{"propositions":[],"lastnames":["Najjar"],"firstnames":["Amro"],"suffixes":[]},{"propositions":[],"lastnames":["Omicini"],"firstnames":["Andrea"],"suffixes":[]},{"propositions":[],"lastnames":["Aydogan"],"firstnames":["Reyhan"],"suffixes":[]},{"propositions":[],"lastnames":["Carli"],"firstnames":["Rachele"],"suffixes":[]},{"propositions":[],"lastnames":["Ciatto"],"firstnames":["Giovanni"],"suffixes":[]},{"propositions":[],"lastnames":["Mualla"],"firstnames":["Yazan"],"suffixes":[]},{"propositions":[],"lastnames":["Främling"],"firstnames":["Kary"],"suffixes":[]}],"title":"Dialogue Explanations for Rule-Based AI Systems","booktitle":"Explainable and Transparent AI and Multi-Agent Systems","year":"2023","publisher":"Springer Nature Switzerland","address":"Cham","pages":"59–77","abstract":"The need for AI systems to explain themselves is increasingly recognised as a priority, particularly in domains where incorrect decisions can result in harm and, in the worst cases, death. Explainable Artificial Intelligence (XAI) tries to produce human-understandable explanations for AI decisions. However, most XAI systems prioritize factors such as technical complexities and research-oriented goals over end-user needs, risking information overload. This research attempts to bridge a gap in current understanding and provide insights for assisting users in comprehending the rule-based system's reasoning through dialogue. The hypothesis is that employing dialogue as a mechanism can be effective in constructing explanations. A dialogue framework for rule-based AI systems is presented, allowing the system to explain its decisions by engaging in ``Why?'' and ``Why not?'' questions and answers. We establish formal properties of this framework and present a small user study with encouraging results that compares dialogue-based explanations with proof trees produced by the AI System.","note":"[<span class=\"car\">Computational Agent Responsibility</span>]","isbn":"978-3-031-4087 @InProceedingsSGAI23, author=","key":"EXTRAAMAS23","id":"EXTRAAMAS23","bibbaseid":"anonymous-dialogueexplanationsforrulebasedaisystems-2023","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/autonomy-and-verification/autonomy-and-verification.github.io/master/pubs.bib","dataSources":["iqRbmbCgpDeaBjend","77JvGFZQteoFsRiyX"],"keywords":[],"search_terms":["dialogue","explanations","rule","based","systems"],"title":"Dialogue Explanations for Rule-Based AI Systems","year":2023}