Vichara: Appellate Judgment Prediction and Explanation for the Indian Judicial System

TL;DR

Vichara is a novel AI framework designed for predicting and explaining appellate judgments in the Indian legal system, utilizing structured decision points and interpretability inspired by IRAC to assist legal professionals.

Contribution

The paper introduces Vichara, a new system that predicts appellate decisions and provides structured, interpretable explanations tailored for Indian legal reasoning, outperforming existing benchmarks.

Findings

Vichara achieves high prediction accuracy with GPT-4o mini (F1: 81.5 on PredEx).

Structured explanations improve interpretability and legal reasoning understanding.

Vichara surpasses existing judgment prediction benchmarks on two datasets.

Abstract

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.