Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justice

Azmine Toushik Wasi, Wahid Faisal, Mst Rafia Islam

TL;DR

Bangladesh faces an access-to-justice crisis driven by language barriers, opaque procedures, and high costs. The authors introduce Mina, a multilingual LLM-based legal assistant for Bangladesh that integrates two-stage retrieval-augmented generation, translation, and citation capabilities within a bilingual Bengali–English interface. They rigorously evaluate Mina against all stages of the Bangladesh Bar Council Examinations (MCQ, Written, Viva), showing human-comparable performance and significant cost reductions. The work demonstrates a practical, scalable path to low-resource, domain-specific AI for public-service law, with implications for expanding access to justice beyond Bangladesh.

Abstract

Bangladesh's low-income population faces major barriers to affordable legal advice due to complex legal language, procedural opacity, and high costs. Existing AI legal assistants lack Bengali-language support and jurisdiction-specific adaptation, limiting their effectiveness. To address this, we developed Mina, a multilingual LLM-based legal assistant tailored for the Bangladeshi context. It employs multilingual embeddings and a RAG-based chain-of-tools framework for retrieval, reasoning, translation, and document generation, delivering context-aware legal drafts, citations, and plain-language explanations via an interactive chat interface. Evaluated by law faculty from leading Bangladeshi universities across all stages of the 2022 and 2023 Bangladesh Bar Council Exams, Mina scored 75-80% in Preliminary MCQs, Written, and simulated Viva Voce exams, matching or surpassing average human performance and demonstrating clarity, contextual understanding, and sound legal reasoning. Even under a conservative upper bound, Mina operates at just 0.12-0.61% of typical legal consultation costs in Bangladesh, yielding a 99.4-99.9\% cost reduction relative to human-provided services. These results confirm its potential as a low-cost, multilingual AI assistant that automates key legal tasks and scales access to justice, offering a real-world case study on building domain-specific, low-resource systems and addressing challenges of multilingual adaptation, efficiency, and sustainable public-service AI deployment.

Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justice

TL;DR

Bangladesh faces an access-to-justice crisis driven by language barriers, opaque procedures, and high costs. The authors introduce Mina, a multilingual LLM-based legal assistant for Bangladesh that integrates two-stage retrieval-augmented generation, translation, and citation capabilities within a bilingual Bengali–English interface. They rigorously evaluate Mina against all stages of the Bangladesh Bar Council Examinations (MCQ, Written, Viva), showing human-comparable performance and significant cost reductions. The work demonstrates a practical, scalable path to low-resource, domain-specific AI for public-service law, with implications for expanding access to justice beyond Bangladesh.

Abstract

Bangladesh's low-income population faces major barriers to affordable legal advice due to complex legal language, procedural opacity, and high costs. Existing AI legal assistants lack Bengali-language support and jurisdiction-specific adaptation, limiting their effectiveness. To address this, we developed Mina, a multilingual LLM-based legal assistant tailored for the Bangladeshi context. It employs multilingual embeddings and a RAG-based chain-of-tools framework for retrieval, reasoning, translation, and document generation, delivering context-aware legal drafts, citations, and plain-language explanations via an interactive chat interface. Evaluated by law faculty from leading Bangladeshi universities across all stages of the 2022 and 2023 Bangladesh Bar Council Exams, Mina scored 75-80% in Preliminary MCQs, Written, and simulated Viva Voce exams, matching or surpassing average human performance and demonstrating clarity, contextual understanding, and sound legal reasoning. Even under a conservative upper bound, Mina operates at just 0.12-0.61% of typical legal consultation costs in Bangladesh, yielding a 99.4-99.9\% cost reduction relative to human-provided services. These results confirm its potential as a low-cost, multilingual AI assistant that automates key legal tasks and scales access to justice, offering a real-world case study on building domain-specific, low-resource systems and addressing challenges of multilingual adaptation, efficiency, and sustainable public-service AI deployment.

Paper Structure

This paper contains 74 sections, 1 equation, 7 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. Methodology: Mina
  4. Architecture Design
  5. Retrieval-Augmented Generation (RAG)
  6. Agents
  7. Tools
  8. LLM Integration and Prompts
  9. Adaptive Agent Workflow
  10. Experiments and Evaluation
  11. Evaluation Setup
  12. Evaluation Metrics
  13. Baselines and Human Performance
  14. Results and Findings
  15. Error Analysis
  16. ...and 59 more sections

Figures (7)

  • Figure 1: System Architecture and Workflow of our Multilingual Legal Assistant Agent for Bangladesh
  • Figure 2: Error Analysis (Command-A model examples)
  • Figure 3: System Demonstration: UI and deployable system of Mina.
  • Figure 4: Breaking Down a Written Full Answer (Command-A, Two Step; Examiner 2)
  • Figure 5: Written exam examples for qualitative error analysis (Part 1)
  • ...and 2 more figures