DEFEND U: AI POWERED LEGAL ADVISOR FOR THE INDIAN LEGAL CONTEXT

  • Unique Paper ID: 206625
  • Volume: 13
  • Issue: 2
  • PageNo: 2967-2973
  • Abstract:
  • Defend U is an AI-powered legal intelligence platform developed to bridge the critical gap between legal complexity and citizen access in India. Unlike conventional legal information retrieval systems, Defend U not only provides real-time search and retrieval of relevant Indian case laws and statutes but also delivers AI-driven summarization, semantic analysis, and structured insights from judicial documents. The system integrates a FastAPI backend, FAISS-based semantic search, Sentence-BERT for query encoding, lexical keyword search with section boosting, and Reciprocal Rank Fusion for hybrid retrieval, followed by Cross-Encoder re-ranking using the ms-marco model to maximize retrieval precision. A Neo4j knowledge graph maps relationships between legal acts, sections, and precedents. For pro-se users, the platform generates actionable legal roadmaps, identifies applicable IPC sections, and provides multilingual support for over 10 Indian languages through optimized batch translation. Built on an asynchronous high-performance architecture using the Llama 3.3 70B model via Groq Cloud, Defend U offers a reliable, scalable, and comprehensive solution that combines automated legal document analysis, knowledge graph navigation, and seamless connectivity for citizens navigating the Indian legal system.

Copyright & License

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.

BibTeX

@article{206625,
        author = {Alan Joseph and Alan Jose and Abhijith R Nair and Albin Jose and Aswathy R},
        title = {DEFEND U: AI POWERED LEGAL ADVISOR FOR THE INDIAN LEGAL CONTEXT},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {2967-2973},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206625},
        abstract = {Defend U is an AI-powered legal intelligence platform developed to bridge the critical gap between legal complexity and citizen access in India. Unlike conventional legal information retrieval systems, Defend U not only provides real-time search and retrieval of relevant Indian case laws and statutes but also delivers AI-driven summarization, semantic analysis, and structured insights from judicial documents. The system integrates a FastAPI backend, FAISS-based semantic search, Sentence-BERT for query encoding, lexical keyword search with section boosting, and Reciprocal Rank Fusion for hybrid retrieval, followed by Cross-Encoder re-ranking using the ms-marco model to maximize retrieval precision. A Neo4j knowledge graph maps relationships between legal acts, sections, and precedents. For pro-se users, the platform generates actionable legal roadmaps, identifies applicable IPC sections, and provides multilingual support for over 10 Indian languages through optimized batch translation. Built on an asynchronous high-performance architecture using the Llama 3.3 70B model via Groq Cloud, Defend U offers a reliable, scalable, and comprehensive solution that combines automated legal document analysis, knowledge graph navigation, and seamless connectivity for citizens navigating the Indian legal system.},
        keywords = {Artificial Intelligence, Cross-Encoder Re-ranking, FAISS, FastAPI, Indian Legal System, Knowledge Graph, Large Language Models, Legal Judgment Summarization, Natural Language Processing, Neo4j, Pro-Se Assistance, Reciprocal Rank Fusion, Retrieval-Augmented Generation, Semantic Search, Sentence-BERT.},
        month = {July},
        }

Cite This Article

Joseph, A., & Jose, A., & Nair, A. R., & Jose, A., & R, A. (2026). DEFEND U: AI POWERED LEGAL ADVISOR FOR THE INDIAN LEGAL CONTEXT. International Journal of Innovative Research in Technology (IJIRT), 13(2), 2967–2973.

Related Articles