{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T16:45:22Z","timestamp":1768322722603,"version":"3.49.0"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643685625","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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":[[2024,12,5]]},"abstract":"<jats:p>Retrieval-Augmented Generation (RAG) systems have shown potential in improving legal question-answering applications. However, they often struggle to provide precise information for legal queries, as broad-topic relevance may not always align with contextual usefulness. To address this challenge, we introduce Constrained Retrieval-Augmented Generation (ConsRAG), a novel approach that employs aspect-based constraints during both retrieval and generation phases. ConsRAG aims to enhance precision and contextual relevance in legal outputs through these constraints and an iterative backtracking mechanism. Our experiments suggest that ConsRAG may offer improvements over existing systems in terms of accuracy and relevance of retrieved documents. This paper presents the framework, implementation, and evaluation of ConsRAG, exploring its potential to enhance the reliability of legal AI applications.<\/jats:p>","DOI":"10.3233\/faia241263","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:01:06Z","timestamp":1733443266000},"source":"Crossref","is-referenced-by-count":2,"title":["ConsRAG: Minimize LLM Hallucinations in the Legal Domain"],"prefix":"10.3233","author":[{"given":"Ha-Thanh","family":"Nguyen","sequence":"first","affiliation":[{"name":"Center for Juris-Informatics, ROIS-DS, Tokyo, Japan"},{"name":"Research and Development Center for Large Language Models, NII, Tokyo, Japan"}]},{"given":"Ken","family":"Satoh","sequence":"additional","affiliation":[{"name":"Center for Juris-Informatics, ROIS-DS, Tokyo, Japan"}]}],"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\/FAIA241263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:01:07Z","timestamp":1733443267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA241263"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9781643685625"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia241263","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]}}}