{"type":"ScholarlyArticle","title":"Explaining Arguments’ Strength: Unveiling the Role of Attacks and Supports","authors":[{"name":"Xiang Yin","slug":"xiang-yin","given":"Xiang","family":"Yin","affiliation":"Department of Computing , Imperial College London , UK"},{"name":"Nico Potyka","slug":"nico-potyka","given":"Nico","family":"Potyka","affiliation":"School of Computer Science and Informatics , Cardiff University , UK"},{"name":"Francesca Toni","slug":"francesca-toni","given":"Francesca","family":"Toni","affiliation":"Department of Computing , Imperial College London , UK"}],"abstract":"Quantitatively explaining the strength of arguments under gradual semantics has recently received increasing attention. Specifically, several works in the literature provide quantitative explanations by computing the attribution scores of arguments. These works disregard the importance of attacks and supports, even though they play an essential role when explaining arguments' strength. In this paper, we propose a novel theory of Relation Attribution Explanations (RAEs), adapting Shapley values from game theory to offer fine-grained insights into the role of attacks and supports in quantitative  bipolar argumentation towards obtaining the arguments' strength. We show that RAEs satisfy several desirable properties. We also propose a probabilistic algorithm to approximate RAEs efficiently. Finally, we show the application value of RAEs in fraud detection and large language models case studies.","doi":"10.24963/ijcai.2024/401","url":"https://ijcai.org/proceedings/2024/401","pdf":"https://ijcai.org/proceedings/2024/0401.pdf","markdown":"https://ijcai.org/proceedings/2024/401.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/401","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":401,"pages":{"first":3622,"last":3630},"keywords":["AI Ethics, Trust, Fairness: ETF: Explainability and interpretability","Knowledge Representation and Reasoning: KRR: Argumentation"],"videos":[],"references":[{"position":1,"raw":"[Albini et al., 2020] Emanuele Albini, Piyawat Lertvit- tayakumjorn, Antonio Rago, and Francesca Toni. Deep argumentative explanations. arXiv:2012.05766, 2020.","title":"Deep argumentative explanations","authors":"Emanuele Albini, Piyawat Lertvittayakumjorn, Antonio Rago, Francesca Toni","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Amgoud and Ben-Naim, 2018] Leila Amgoud and Jonathan Ben-Naim. Evaluation of arguments in weighted bipolar graphs. International Journal of Approximate Reasoning, 99:39-55, 2018.","title":"Leila Amgoud and Jonathan Ben-Naim. Evaluation of arguments in weighted bipolar graphs","authors":"Ben-Naim Amgoud","year":"2018","venue":"International Journal of Approximate Reasoning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Amgoud et al., 2017] Leila Amgoud, Jonathan Ben-Naim, and Srdjan Vesic. Measuring the intensity of attacks in argumentation graphs with shapley value. In International Joint Conference on Artificial Intelligence (IJCAI), pages 63-69, 2017.","title":"Measuring the intensity of attacks in argumentation graphs with shapley value","authors":"Leila Amgoud, Jonathan Ben-Naim, Srdjan Vesic","year":"2017","venue":"International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":"/proceedings/2017/10"},{"position":4,"raw":"[Ancona et al., 2017] Marco Ancona, Enea Ceolini, Cengiz Öztireli, and Markus Gross. Towards better understand- ing of gradient-based attribution methods for deep neural networks. arXiv preprint arXiv:1711.06104, 2017.","title":"Towards better understanding of gradient-based attribution methods for deep neural networks","authors":"Marco Ancona, Enea Ceolini, Cengiz Öztireli, Markus Gross","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ayoobi et al., 2023] Hamed Ayoobi, Nico Potyka, and Francesca Toni. Sparx: Sparse argumentative explanations for neural networks. In European Conference on Artificial Intelligence (ECAI), volume 372, pages 149-156, 2023.","title":"Sparx: Sparse argumentative explanations for neural networks","authors":"Hamed Ayoobi, Nico Potyka, Francesca Toni","year":"2023","venue":"European Conference on Artificial Intelligence (ECAI)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Baroni et al., 2015] Pietro Baroni, Marco Romano, Francesca Toni, Marco Aurisicchio, and Giorgio Bertanza. Automatic evaluation of design alternatives with quantita- tive argumentation. Argument & Computation, 6:24-49, 2015.","title":"Automatic evaluation of design alternatives with quantitative argumentation","authors":"Pietro Baroni, Marco Romano, Francesca Toni, Marco Aurisicchio, Giorgio Bertanza","year":"2015","venue":"Argument & Computation","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Baroni et al., 2019] Pietro Baroni, Antonio Rago, and Francesca Toni. From fine-grained properties to broad principles for gradual argumentation: A principled spec- trum. International Journal of Approximate Reasoning, 105:252-286, 2019.","title":"From fine-grained properties to broad principles for gradual argumentation: A principled spectrum","authors":"Pietro Baroni, Antonio Rago, Francesca Toni","year":"2019","venue":"International Journal of Approximate Reasoning","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Cayrol and Lagasquie-Schiex, 2013] Claudette Cayrol and Marie-Christine Lagasquie-Schiex. Bipolarity in argumen- tation graphs: Towards a better understanding. Interna- tional Journal of Approximate Reasoning, 54:876-899, 2013.","title":"Claudette Cayrol and Marie-Christine Lagasquie-Schiex. Bipolarity in argumentation graphs: Towards a better understanding","authors":"Lagasquie-Schiex Cayrol","year":"2013","venue":"International Journal of Approximate Reasoning","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Chen et al., 2022] Zixi Chen, Varshini Subhash, Marton Havasi, Weiwei Pan, and Finale Doshi-Velez. What makes a good explanation?: A harmonized view of properties of explanations. In Workshop on Trustworthy and Socially Responsible Machine Learning, 2022.","title":"What makes a good explanation?: A harmonized view of properties of explanations","authors":"Zixi Chen, Varshini Subhash, Marton Havasi, Weiwei Pan, Finale Doshi-Velez","year":"2022","venue":"Workshop on Trustworthy and Socially Responsible Machine Learning","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Chi et al., 2021] Haixiao Chi, Yiwei Lu, Beishui Liao, Liaosa Xu, and Yaqi Liu. An optimized quantitative argu- mentation debate model for fraud detection in e-commerce transactions. IEEE Intelligent Systems, 36:52-63, 2021.","title":"An optimized quantitative argumentation debate model for fraud detection in e-commerce transactions","authors":"Chi","year":"2021","venue":"IEEE Intelligent Systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Cocarascu et al., 2019] Oana Cocarascu, Antonio Rago, and Francesca Toni. Extracting dialogical explanations for re- view aggregations with argumentative dialogical agents. In International Conference on Autonomous Agents and MultiAgent Systems (AAMAS), pages 1261-1269, 2019.","title":"Extracting dialogical explanations for review aggregations with argumentative dialogical agents","authors":"Cocarascu","year":"2019","venue":"International Conference on Autonomous Agents and MultiAgent Systems (AAMAS)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Čyras et al., 2021] Kristijonas Čyras, Antonio Rago, Emanuele Albini, Pietro Baroni, and Francesca Toni. Argumentative XAI: a survey. In International Joint Conference on Artificial Intelligence (IJCAI), pages 4392-4399, 2021.","title":"Argumentative XAI: a survey","authors":"Čyras","year":"2021","venue":"International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":"/proceedings/2021/600"},{"position":13,"raw":"[Čyras et al., 2022] Kristijonas Čyras, Timotheus Kampik, and Qingtao Weng. Dispute trees as explanations in quanti- tative (bipolar) argumentation. In International Workshop on Argumentation for eXplainable AI, volume 3209, pages 1-12, 2022.","title":"Kristijonas Čyras, Timotheus Kampik, and Qingtao Weng. Dispute trees as explanations in quantitative (bipolar) argumentation","authors":"Čyras","year":"2022","venue":"International Workshop on Argumentation for eXplainable AI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Delobelle and Villata, 2019] Jérôme Delobelle and Serena Villata. Interpretability of gradual semantics in abstract argumentation. In Symbolic and Quantitative Approaches to Reasoning with Uncertainty: European Conference (EC- SQARU), volume 11726, pages 27-38, 2019.","title":"Interpretability of gradual semantics in abstract argumentation","authors":"Villata Delobelle, Jérôme Delobelle, Serena Villata","year":"2019","venue":"Symbolic and Quantitative Approaches to Reasoning with Uncertainty: European Conference (EC-SQARU)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Dung, 1995] Phan Minh Dung. On the acceptability of argu- ments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games. Artificial Intelli- gence, 77:321-358, 1995.","title":"On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games","authors":"Phan Minh, Dung","year":"1995","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Dunne et al., 2011] Paul E Dunne, Anthony Hunter, Pe- ter McBurney, Simon Parsons, and Michael Wooldridge. Weighted argument systems: Basic definitions, algorithms, and complexity results. Artificial Intelligence, 175:457- 486, 2011.","title":"Weighted argument systems: Basic definitions, algorithms, and complexity results","authors":"Anthony Paul E Dunne, Peter Hunter, Simon Mcburney, Michael Parsons, Wooldridge","year":"2011","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Gut and Gut, 2005] Allan Gut and Allan Gut. Probability: a graduate course, volume 200. 2005.","title":"Allan Gut and Allan Gut. Probability: a graduate course","authors":"Gut Gut","year":"2005","venue":"Allan Gut and Allan Gut. Probability: a graduate course","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Leite and Martins, 2011] Joao Leite and Joao Martins. So- cial abstract argumentation. In International Joint Confer- ence on Artificial Intelligence (IJCAI), pages 2287-2292, 2011.","title":"Social abstract argumentation","authors":"Joao Leite, Joao Martins","year":"2011","venue":"International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":"/proceedings/2011/381"},{"position":19,"raw":"[Lundberg and Lee, 2017] Scott M Lundberg and Su-In Lee. A unified approach to interpreting model predictions. Ad- vances in neural information processing systems, 30:4765- 4774, 2017.","title":"A unified approach to interpreting model predictions","authors":"M Scott, Su-In Lundberg, Lee","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Maschler et al., 2013] Michael Maschler, Eilon Solan, and Shmuel Zamir. Game Theory. 2013.","title":"Game Theory","authors":"Michael Maschler, Eilon Solan, Shmuel Zamir","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Mittelstadt et al., 2019] Brent Mittelstadt, Chris Russell, and Sandra Wachter. Explaining explanations in ai. In Confer- ence on fairness, accountability, and transparency, pages 279-288, 2019.","title":"Explaining explanations in ai","authors":"Brent Mittelstadt, Chris Russell, Sandra Wachter","year":"2019","venue":"Conference on fairness, accountability, and transparency","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Mossakowski and Neuhaus, 2018] Till Mossakowski and Fabian Neuhaus. Modular semantics and characteristics for bipolar weighted argumentation graphs. arXiv preprint arXiv:1807.06685, 2018.","title":"Till Mossakowski and Fabian Neuhaus. Modular semantics and characteristics for bipolar weighted argumentation graphs","authors":"Neuhaus Mossakowski","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Naveed et al., 2023] Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Nick Barnes, and Ajmal Mian. A comprehensive overview of large language models. arXiv preprint arXiv:2307.06435, 2023.","title":"A comprehensive overview of large language models","authors":"Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Nick Barnes, Ajmal Mian","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[OpenAI, 2022] OpenAI. Introducing chatgpt. 2022.","title":"OpenAI. Introducing chatgpt","authors":"Openai","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Potyka et al., 2023] Nico Potyka, Xiang Yin, and Francesca Toni. Explaining random forests using bipolar argumenta- tion and markov networks. In AAAI Conference on Artificial Intelligence, volume 37, pages 9453-9460, 2023.","title":"Explaining random forests using bipolar argumentation and markov networks","authors":"Nico Potyka, Xiang Yin, Francesca Toni","year":"2023","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Potyka, 2018] Nico Potyka. Continuous dynamical systems for weighted bipolar argumentation. In International Con- ference on Principles of Knowledge Representation and Reasoning (KR), pages 148-157, 2018.","title":"Continuous dynamical systems for weighted bipolar argumentation","authors":"Nico Potyka","year":"2018","venue":"International Conference on Principles of Knowledge Representation and Reasoning (KR)","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Potyka, 2019] Nico Potyka. Extending modular semantics for bipolar weighted argumentation. In International Con- ference on Autonomous Agents and MultiAgent Systems, AAMAS, pages 1722-1730, 2019.","title":"Extending modular semantics for bipolar weighted argumentation","authors":"Nico Potyka","year":"2019","venue":"International Conference on Autonomous Agents and MultiAgent Systems, AAMAS","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Potyka, 2021] Nico Potyka. Interpreting neural networks as quantitative argumentation frameworks. In AAAI Con- ference on Artificial Intelligence, volume 35, pages 6463- 6470, 2021.","title":"Nico Potyka. Interpreting neural networks as quantitative argumentation frameworks","authors":"Potyka","year":"2021","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Rago et al., 2016] Antonio Rago, Francesca Toni, Marco Au- risicchio, and Pietro Baroni. Discontinuity-free decision support with quantitative argumentation debates. In In- ternational Conference on the Principles of Knowledge Representation and Reasoning (KR), pages 63-73, 2016.","title":"Discontinuity-free decision support with quantitative argumentation debates","authors":"Rago","year":"2016","venue":"International Conference on the Principles of Knowledge Representation and Reasoning (KR)","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Shapley, 1951] Lloyd S Shapley. Notes on the N-person Game. 1951.","title":"Notes on the N-person Game","authors":"S Lloyd, Shapley","year":"1951","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Yin et al., 2023] Xiang Yin, Nico Potyka, and Francesca Toni. Argument attribution explanations in quantitative bipolar argumentation frameworks. In European Confer- ence on Artificial Intelligence (ECAI), volume 372, pages 2898-2905, 2023.","title":"Argument attribution explanations in quantitative bipolar argumentation frameworks","authors":"Xiang Yin, Nico Potyka, Francesca Toni","year":"2023","venue":"European Conference on Artificial Intelligence (ECAI)","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhang et al., 2021] Hao Zhang, Yichen Xie, Longjie Zheng, Die Zhang, and Quanshi Zhang. Interpreting multivariate shapley interactions in dnns. In AAAI Conference on Artifi- cial Intelligence, volume 35, pages 10877-10886, 2021.","title":"Interpreting multivariate shapley interactions in dnns","authors":"Hao Zhang, Yichen Xie, Longjie Zheng, Die Zhang, Quanshi Zhang","year":"2021","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}