{"version":1,"type":"story","url":"https://digestai.news/story/researchers-propose-lego-framework-for-legal-reasoning","json":"https://digestai.news/story/researchers-propose-lego-framework-for-legal-reasoning.json","markdown":"https://digestai.news/story/researchers-propose-lego-framework-for-legal-reasoning.md","slug":"researchers-propose-lego-framework-for-legal-reasoning","headline":"Researchers propose LEGO framework for legal reasoning","summary":"Researchers have introduced LEGO, a dual-module framework designed to improve how large language models handle complex legal reasoning. The system addresses two main limitations in current approaches: existing retrieval methods often miss the normative relationships between legal provisions, and standard Chain-of-Thought prompting may generate plausible but structurally unsound rationales.\n\nLEGO combines Legal Expert GraphRAG, which uses an expert-annotated civil code graph to extract specific provision subgraphs, with Expert Chain-of-Thought, which structures reasoning into Provision-Fact-Conclusion steps. The framework utilizes a Qwen3-8B backbone model.\n\nIn testing, LEGO achieved 40.53% exact-match accuracy on the LawExamQACivil benchmark. This performance outperforms evaluated RAG and CoT baselines and is comparable to larger models, while maintaining robustness on multi-hop questions. The authors also report that LEGO yields the best results among evaluated baselines on open-ended benchmarks. Code and datasets are available on GitHub.","keyPoints":["LEGO combines expert-annotated GraphRAG and structured Chain-of-Thought for legal reasoning.","Using a Qwen3-8B backbone, LEGO achieves 40.53% exact-match accuracy on LawExamQACivil.","The framework outperforms standard RAG and CoT baselines in the study."],"whyItMatters":"This research offers a structured approach to improving LLM reliability in high-stakes legal domains, potentially reducing hallucinations and enhancing the accuracy of automated legal analysis tools.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":["Qwen3-8B"],"people":[]},"firstPublishedAt":"2026-09-24T04:00:00Z","updatedAt":"2026-09-24T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.CL","title":"LEGO: Synergizing Expert GraphRAG and Expert Chain-of-Thought for Legal Reasoning","url":"https://arxiv.org/abs/2609.27009","publishedAt":"2026-09-24T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers propose LEGO framework for legal reasoning\", 24 September 2026, https://digestai.news/story/researchers-propose-lego-framework-for-legal-reasoning","publisher":"Digest AI","title":"Researchers propose LEGO framework for legal reasoning","datePublished":"2026-09-24T04:00:00Z","url":"https://digestai.news/story/researchers-propose-lego-framework-for-legal-reasoning"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}