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

TL;DR

Vichara tackles appellate judgment prediction in India's high-backlog judiciary by introducing a six-stage, prompt-driven pipeline that converts case proceedings into discrete decision points and IRAC-style explanations. The framework combines rhetorical role classification, case context construction, and decision-point extraction to generate present-court rulings and predictions, with explanations structured along the IRAC framework. Empirical results on PredEx and ILDC_expert show strong predictive performance across multiple large-language models, notably GPT-4o mini, and human evaluators rate the explanations highly in Clarity, Linking, and Usefulness. The work demonstrates that structured, explainable AI tooling can enhance transparency and trust in judicial AI, while also indicating that smaller models can be viable for deployment with careful design and prompting.

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.

Figures (3)

• Figure 1: Vichara’s appellate judgment prediction and explanation for a sample case excerpt.
• Figure 2: Vichara flow diagram
• Figure 3: Outputs at each processing step for an example court case.