{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:36:05Z","timestamp":1761176165973,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Large language models (LLMs) excel at complex reasoning and achieve human-like performance in many natural language processing tasks. However, they still struggle to reason effectively when faced with inconsistent or contradictory information. This capability gap raises significant concerns for real-world applications where reliable decision-making depends on reconciling conflicting evidence, such as legal analysis, medical diagnosis, and commonsense reasoning. In this paper, we focus on defeasible reasoning in natural language, a task that challenges LLMs to handle and resolve contradictory information. To improve the defeasible reasoning capability of LLMs, we propose LLM-ASPIC+, a framework combining neural language understanding with formal argumentation. Our framework harnesses LLMs\u2019 capacity for grounding and contextual reasoning while integrating formal argumentation frameworks to establish systematic conflict resolution mechanisms lacking in LLMs. We also create MineQA, a newly synthesized dataset designed to evaluate multi-step defeasible reasoning under both strict and defeasible rules. LLM-ASPIC+ achieves state-of-the-art results on multi-step defeasible reasoning, with 87.1% accuracy on BoardGameQA-2 and 82.6% on BoardGameQA-3. These results show that integrating neural language models with formal argumentation effectively supports defeasible reasoning in natural language.<\/jats:p>","DOI":"10.3233\/faia250981","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:47:44Z","timestamp":1761126464000},"source":"Crossref","is-referenced-by-count":0,"title":["LLM-ASPIC+: A Neuro-Symbolic Framework for Defeasible Reasoning"],"prefix":"10.3233","author":[{"given":"Xiaotong","family":"Fang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}]},{"given":"Zhaoqun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Philosophy, Zhejiang University"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Philosophy, Zhejiang University"}]},{"given":"Beishui","family":"Liao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"},{"name":"School of Philosophy, Zhejiang University"},{"name":"The State Key Lab of Brain-Machine Intelligence, Zhejiang University"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA250981","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:47:45Z","timestamp":1761126465000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA250981"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia250981","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}