{"type":"ScholarlyArticle","title":"Most General Explanations of Tree Ensembles","authors":[{"name":"Yacine Izza","slug":"yacine-izza","given":"Yacine","family":"Izza","affiliation":""},{"name":"Akexey Ignatiev","slug":"akexey-ignatiev","given":"Akexey","family":"Ignatiev","affiliation":""},{"name":"Sasha Rubin","slug":"sasha-rubin","given":"Sasha","family":"Rubin","affiliation":""},{"name":"Joao Marques-Silva","slug":"joao-marques-silva","given":"Joao","family":"Marques-Silva","affiliation":""},{"name":"Peter J. Stuckey","slug":"peter-j-stuckey","given":"Peter J.","family":"Stuckey","affiliation":""}],"abstract":"Explainable Artificial Intelligence (XAI) is critical for  attaining trust in the operation of AI systems. A key question of an AI system is ``why was this decision  made this way''. Formal approaches to XAI use a formal model of the AI system  to identify abductive explanations.  While abductive explanations   may be applicable to a large number of inputs sharing the same concrete values, more general explanations may be preferred for  numeric inputs. \r\n So-called inflated abductive explanations give intervals for  each feature ensuring that any input whose values fall withing these   intervals is still guaranteed to make the same prediction. Inflated explanations cover a larger portion of the input space, and  hence are deemed more general explanations. But there can be many (inflated) abductive explanations for an instance.  Which is the best? In this paper, we show how to find a most general abductive explanation for an AI decision. This explanation covers as much of the input space as possible, while still being a correct formal explanation of the model's behaviour. Given that we only want to give a human one explanation for a decision, the most general explanation gives us the explanation with the broadest applicability, and hence the one most likely to seem sensible.","doi":"10.24963/ijcai.2025/608","url":"https://ijcai.org/proceedings/2025/608","pdf":"https://ijcai.org/proceedings/2025/0608.pdf","markdown":"https://ijcai.org/proceedings/2025/608.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/608","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":608,"pages":{"first":5463,"last":5471},"keywords":["Knowledge Representation and Reasoning: KRR: Diagnosis and abductive reasoning","Constraint Satisfaction and Optimization: CSO: Constraint satisfaction","Constraint Satisfaction and Optimization: CSO: Constraint optimization problems","Machine Learning: ML: Explainable/Interpretable machine learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}