{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:15:05Z","timestamp":1758672905578,"version":"3.44.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>Abductive Learning (ABL), a prominent neural-symbolic learning algorithm, integrates perception models with logical reasoning via intermediate symbolic concepts, substantially improving the interpretability and generalization of AI systems. However, a significant challenge in this domain is the issue of reasoning shortcuts, where the system achieve high final prediction accuracy but generate incorrect intermediate concept inferences, severely\n\nundermining ABL\u2019s interpretability and generalization capabilities. Current mitigation methods to this problem often neglect potential correlations among training samples, leading to suboptimal performances. This paper innovatively reveals that simple samples can facilitate the learning of intermediate concepts in complex samples, prompting our proposed method Curriculum Abductive Learning (CurABL) technique. This approach employs a curriculum training strategy, integrating a knowledge transfer mechanism from simple to complex samples, effectively addressing the issue of reasoning shortcuts. Comprehensive experimental results demonstrate that the CurABL method substantially improves the ABL framework\u2019s capability to extract intermediate concepts especially in difficult tasks and accelerates the training convergence rate, thus markedly enhancing its robustness against reasoning shortcuts.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/727","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"6533-6541","source":"Crossref","is-referenced-by-count":0,"title":["Curriculum Abductive Learning for Mitigating Reasoning Shortcuts"],"prefix":"10.24963","author":[{"given":"Wen-Da","family":"Wei","sequence":"first","affiliation":[{"name":"Nanjing university"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Wen","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing university"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie-Jing","family":"Shao","sequence":"additional","affiliation":[{"name":"Nanjing university"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lan-Zhe","family":"Guo","sequence":"additional","affiliation":[{"name":"Nanjing university"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2025","name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","start":{"date-parts":[[2025,8,16]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:34:59Z","timestamp":1758627299000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/727"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/727","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}