Legal Assist AI: Leveraging Transformer-Based Model for Effective Legal Assistance

2025-05-28

AI Summary

Widespread legal illiteracy and limited access to authoritative legal information severely impede legal service accessibility across India. To address this, we introduce the first large language model (LLM) specifically designed for India’s legal ecosystem, trained on a comprehensive corpus encompassing the Indian Constitution, the Bharatiya Nyaya Sanhita (BNS, 2023), and the Bharatiya Nagarik Suraksha Sanhita (BNSS, 2023). Our approach synergistically integrates retrieval-augmented generation (RAG) with domain-adaptive fine-tuning to mitigate hallucination, enhance factual consistency, and improve legal reasoning fidelity. Evaluated on the All India Bar Examination (AIBE) benchmark, our model achieves a score of 60.08—surpassing both GPT-3.5 Turbo and Mistral 7B—demonstrating state-of-the-art performance in legal question answering accuracy and reliability. This work establishes a foundational, India-specific LLM for equitable, trustworthy, and contextually grounded legal assistance.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Philosophy and Ethics of AI: AI & Law, Justice, Regulation & Governance

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Pursuit of accessible legal assistance in India faces a critical gap, as many citizens struggle to leverage their legal rights due to limited awareness and access to relevant legal information. This paper introduces Legal Assist AI, a transformer-based model designed to bridge this gap by offering effective legal assistance through large language models (LLMs). The system retrieves relevant legal information from a curated database and generates accurate responses, enabling effective assistance for diverse users, including legal professionals, scholars, and the general public. The model was fine-tuned on extensive datasets from the Indian legal domain, including Indian Constitution, Bharatiya Nyaya Sanhita (BNS), Bharatiya Nagarik Suraksha Sanhita (BNSS) and so forth, providing a robust understanding of the complexities of Indian law. By incorporating domain-specific legal datasets, the proposed model demonstrated remarkable efficiency and specialization in legal Question-Answering. The model was evaluated against state-of-the-art models such as GPT-3.5 Turbo and Mistral 7B, achieving a 60.08% score on the AIBE, outperforming its competitors in legal reasoning and accuracy. Unlike other models, Legal Assist AI avoided common issues such as hallucinations, making it highly reliable for practical legal applications. It showcases the model's applicability in real-world legal scenarios, with future iterations aiming to enhance performance and expand its dataset to cover a broader range of multilingual and case-specific queries as well.

Problem

• Bridging India's legal assistance gap with AI
• Providing accurate legal information via LLMs
• Enhancing legal reasoning and reducing hallucinations

Innovation

• Transformer-based model for legal assistance
• Fine-tuned on Indian legal datasets
• Outperforms GPT-3.5 Turbo in accuracy