Vichara：印度司法系统上诉判决预测与解释
Vichara: Appellate Judgment Prediction and Explanation for the Indian Judicial System
AI总结：
Vichara通过结构化方法预测和解释印度司法系统中的上诉判决，利用大型语言模型在两个数据集上取得优异表现，尤其在可解释性方面表现突出。
摘要：
在像印度这样的司法辖区，法院面临大量的案件积压，人工智能为法律判决预测提供了变革性的潜力。这一积压中关键的子集包括上诉案件，这些案件是由高等法院对低级法院的裁定进行审查后作出的正式决定。为此，我们提出了Vichara，一个专门针对印度司法系统的新型框架，用于预测和解释上诉判决。Vichara处理以英语书写的上诉案件文本文档，并将它们分解为决策点。决策点是离散的法律判断，涵盖法律问题、决定权、结果、推理和时间背景。结构化的表示方法隔离了核心判断及其背景，从而能够实现准确的预测和可解释的解释。Vichara的解释遵循受IRAC（问题-规则-应用-结论）框架启发并适应于印度法律推理的结构化格式。这增强了可解释性，使法律专业人士能够高效地评估预测的可靠性。我们对两个数据集进行了评估，PredEx和印度法律文档语料库（ILDC_expert）的专家注释子集，使用了四个大型语言模型：GPT-4o mini、Llama-3.1-8B、Mistral-7B和Qwen2.5-7B。Vichara在两个数据集上均超过了现有的判决预测基准，其中GPT-4o mini在PredEx上实现了最高性能（F1：81.5，在ILDC_expert上为80.3），随后是Llama-3.1-8B。对生成解释在清晰度、关联性和有用性指标上的人工评估突显了GPT-4o mini在可解释性上的优势。
英文摘要：
In jurisdictions like India, where courts face an extensive backlog of cases, artificial intelligence offers transformative potential for legal judgment prediction. A critical subset of this backlog comprises appellate cases, which are formal decisions issued by higher courts reviewing the rulings of lower courts. To this end, we present Vichara, a novel framework tailored to the Indian judicial system that predicts and explains appellate judgments. Vichara processes English-language appellate case proceeding documents and decomposes them into decision points. Decision points are discrete legal determinations that encapsulate the legal issue, deciding authority, outcome, reasoning, and temporal context. The structured representation isolates the core determinations and their context, enabling accurate predictions and interpretable explanations. Vichara's explanations follow a structured format inspired by the IRAC (Issue-Rule-Application-Conclusion) framework and adapted for Indian legal reasoning. This enhances interpretability, allowing legal professionals to assess the soundness of predictions efficiently. We evaluate Vichara on two datasets, PredEx and the expert-annotated subset of the Indian Legal Documents Corpus (ILDC_expert), using four large language models: GPT-4o mini, Llama-3.1-8B, Mistral-7B, and Qwen2.5-7B. Vichara surpasses existing judgment prediction benchmarks on both datasets, with GPT-4o mini achieving the highest performance (F1: 81.5 on PredEx, 80.3 on ILDC_expert), followed by Llama-3.1-8B. Human evaluation of the generated explanations across Clarity, Linking, and Usefulness metrics highlights GPT-4o mini's superior interpretability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
