通过分步验证与纠错提升法律判决预测的逻辑可靠性
LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning
- 分步拆解案件争议点，逐级验证推理逻辑
- 在LLAMA-3.1-70B上使判决一致性从72.37%提升至80.27%
- 适合法律AI研究者与司法智能化开发者参考
法律判决预测（LJP）旨在基于案情和事实做出最终裁决，对司法辅助决策与提升审判效率至关重要。然而现有方法在复杂法律推理中常出现逻辑错误。本文提出LegalReasoner，通过分步验证与纠错机制提升LJP可靠性：首先识别争议点以分解复杂案件，再进行分步推理，并由过程验证器检查每一步的正确性、进展性与潜在视角。发现错误后，采用专家设计的归因与修正策略进行纠正。为训练该模型，我们发布包含58,130个香港法院案例的LegalHK数据集，涵盖争议点标注、分步推理链及过程验证标签。实验表明，LegalReasoner在LLAMA-3.1-70B上使判决一致性从72.37%显著提升至80.27%。数据已公开于https://huggingface.co/datasets/weijiezz/LegalHK。
原文摘要 · Abstract (English)
Legal judgment prediction (LJP) aims to function as a judge by making final rulings based on case claims and facts, which plays a vital role in the judicial domain for supporting court decision-making and improving judicial efficiency. However, existing methods often struggle with logical errors when conducting complex legal reasoning. We propose LegalReasoner, which enhances LJP reliability through step-wise verification and correction of the reasoning process. Specifically, it first identifies dispute points to decompose complex cases, and then conducts step-wise reasoning while employing a process verifier to validate each step's logic from correctness, progressiveness, and potential perspectives. When errors are detected, expert-designed attribution and resolution strategies are applied for correction. To fine-tune LegalReasoner, we release the LegalHK dataset, containing 58,130 Hong Kong court cases with detailed annotations of dispute points, step-by-step reasoning chains, and process verification labels. Experiments demonstrate that LegalReasoner significantly improves concordance with court decisions from 72.37 to 80.27 on LLAMA-3.1-70B. The data is available at https://huggingface.co/datasets/weijiezz/LegalHK.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。