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

2026-02-20

AI Summary

This study addresses the chronic backlog of appellate cases in the Indian judicial system by proposing a structured representation of decision points tailored to its legal context. The approach parses English-language appellate judgments into legal issues, rule applications, and reasoning steps, adapting the IRAC legal reasoning framework to generate interpretable predictions. Leveraging expert-annotated data, the authors evaluate several large language models—including GPT-4o mini, Llama-3.1-8B, Mistral-7B, and Qwen2.5-7B—on the PredEx and ILDC_expert datasets. GPT-4o mini achieves state-of-the-art performance with F1 scores of 81.5 and 80.3, respectively, and human evaluators consistently rank its generated explanations as superior in clarity, relevance, and practical utility.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• appellate judgment prediction
• legal AI
• judicial backlog
• explainable AI
• Indian judicial system

Innovation

• appellate judgment prediction
• decision point decomposition
• structured legal explanation
• IRAC-based reasoning
• legal AI for Indian judiciary