Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{197134,
        author = {D. Pavani Sesharatnam and N. Manohar and B. Raghu Ram and V. Krishna Teja and Dr. Y. Venkat},
        title = {Legal Document Analysis and Question Answering using Retrieval-Augmented Generation (RAG) Framework},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {5741-5747},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197134},
        abstract = {In the modern legal ecosystem, vast volumes of legal documents such as case laws, contracts, and statutes are generated daily, making manual analysis time-consuming and inefficient. This research presents a system for legal document analysis and question answering using the Retrieval-Augmented Generation (RAG) framework. The proposed model integrates information retrieval techniques with advanced natural language processing to provide accurate, context-aware answers from legal texts.
The system preprocesses legal documents through text cleaning, segmentation, and embedding generation, followed by indexing in a vector database. When a user submits a query, relevant document chunks are retrieved and passed to a generative language model to produce precise answers. The approach improves answer reliability by grounding responses in actual legal content, reducing hallucinations commonly seen in standalone language models.
Experimental results demonstrate that the RAG-based system enhances accuracy, relevance, and interpretability in legal question answering tasks. This framework can assist legal professionals, researchers, and students in quickly accessing critical information, thereby improving efficiency and decision-making in legal processes.},
        keywords = {Legal Document Analysis, Retrieval-Augmented Generation (RAG), Natural Language Processing (NLP), Question Answering, Vector Database, Information Retrieval, Legal AI, Text Embeddings},
        month = {April},
        }