🤖 AI Summary
This work proposes a domain-adapted retrieval-augmented generation framework tailored for complex legal question answering grounded in judgments of the Supreme Court of India. The approach innovatively incorporates a rhetorical role–aware text chunking strategy that leverages structural features of legal documents, such as judicial authorship, and integrates multi-path retrieval, cross-encoder reranking, and a query rewriting mechanism informed by query classification and dialogue history to accurately capture user intent. Experimental results demonstrate that the proposed framework significantly outperforms baseline methods in terms of contextual recall and answer relevance, thereby enhancing the system’s accuracy, interpretability, and reliability in intricate legal contexts.
📝 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.