{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T12:10:28Z","timestamp":1764850228001,"version":"3.46.0"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686387","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"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":[[2025,12,2]]},"abstract":"<jats:p>Large language models (LLMs) are significantly limited in causal reasoning in the legal domain. Determining legal liability in autonomous-driving traffic accidents inherently involves complex causal relationships, thereby providing a typical scenario for exploring and enhancing the causal reasoning capabilities of LLMs in legal contexts. In this study, GraphRAG is employed to provide more accurate and interpretable causal reasoning pathways for LLMs to determine legal liability, thereby enhancing their causal reasoning capabilities in the context of determining autonomous-driving traffic accident liability. We construct a knowledge graph from expert-annotated judicial documents using Neo4j and integrate it with LLMs using the LangChain framework. After referencing the legal causal reasoning paths retrieved from similar cases, LLMs could generate causal reasoning processes and final legal liability determinations for unresolved cases. This study could provide insights into judicial practices in autonomous-driving traffic accidents and advance the application of LLM-based causal reasoning in the legal domain.<\/jats:p>","DOI":"10.3233\/faia251625","type":"book-chapter","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T12:05:51Z","timestamp":1764849951000},"source":"Crossref","is-referenced-by-count":0,"title":["A GraphRAG Approach to Enhancing the Ability of Causal Reasoning in Autonomous Driving Cases"],"prefix":"10.3233","author":[{"given":"Jia","family":"Liu","sequence":"first","affiliation":[{"name":"Law School, Huazhong University of Science and Technology, Wuhan, Hubei, China"},{"name":"Hubei Judicial Big Data Research Center, Wuhan, Hubei, China"}]},{"given":"Xingtong","family":"Chen","sequence":"additional","affiliation":[{"name":"Law School, Huazhong University of Science and Technology, Wuhan, Hubei, China"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","Legal Knowledge and Information Systems"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T12:05:51Z","timestamp":1764849951000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251625"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"ISBN":["9781643686387"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251625","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,2]]}}}