# Rhetorical-Role-Aware Retrieval-Augmented Generation for Legal Question Answering over Indian Supreme Court Judgments

Source: [Rhetorical-Role-Aware Retrieval-Augmented Generation for Legal Question Answering over Indian Supreme Court Judgments](<https://www.sota2.com/research/paper/6a795b15a080ff033d3e32c4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-08-11T05:02:11.192Z

Authors: Sayed Ayaan Ahmed Sha, Sangeetha Sivanesan, Anand Kumar Madasamy, Navya Binu

Published: 2026-08-07T05:38:02.000Z

## Abstract

This research paper proposes a Retrieval Augmented Generation (RAG) framework that is specific to the legal field in order to assist interactive retrieval and reason about judgments from the Supreme Court of India. The solution uses an enhanced version of RAG framework which consists of rhetorically based chunking, fusion-based retrieval, and cross encoder reranking methods to increase the relevancy of the information retrieved. In order to improve conversations, the proposed framework uses chat history along with query classification and rewriting in order to understand user intention from successive queries. Additionally, there are features that take into account structural aspects of legal documents, such as isolated names of judges that could have an impact on retrieval quality. The evaluation was done using the DeepEval framework and demonstrated strong performance on metrics including contextual recall and answer relevancy, which proves that the framework is very effective in dealing with legal question-answering tasks that require a lot of context. The results emphasize the importance of domain specific enhancements in developing legal AI systems that are both reliable and explainable.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2608.06828>)

[PDF](<https://arxiv.org/pdf/2608.06828.pdf>)