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

• URL: http://arxiv.org/abs/2511.08605v1
• Date: Thu, 13 Nov 2025 01:00:30 GMT
• Title: Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justice
• Authors: Azmine Toushik Wasi, Wahid Faisal, Mst Rafia Islam,
• Abstract summary: Existing AI legal assistants lack Bengali-language support and jurisdiction-specific adaptation.<n>We developed Mina, a multilingual LLM-based legal assistant tailored for the Bangladeshi context.<n>It employs multilingual embeddings and a RAG-based chain-of-tools framework for retrieval, reasoning, translation, and document generation.
• Score: 5.215285027585101
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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. 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.

Related papers

• LegalOne: A Family of Foundation Models for Reliable Legal Reasoning [54.57434222018289]
  We present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain.<n>LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning.<n>We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI.
  arXiv  Detail & Related papers  (2026-01-31T10:18:32Z)
• Evaluating the Limits of Large Language Models in Multilingual Legal Reasoning [5.902003660308139]
  This work evaluates LLaMA and Gemini on multilingual legal and non-legal benchmarks.<n>We present an open-source, modular evaluation pipeline designed to support multilingual, task-diverse benchmarking.
  arXiv  Detail & Related papers  (2025-09-26T15:19:12Z)
• MizanQA: Benchmarking Large Language Models on Moroccan Legal Question Answering [13.01152821327721]
  This paper introduces MizanQA (pronounced Mizan, meaning "scale" in Arabic), a benchmark to evaluate large language models (LLMs)<n>The dataset draws on Modern Standard Arabic, Islamic Maliki jurisprudence, Moroccan customary law, and French legal influences.<n> Benchmarking experiments with multilingual and Arabic-focused LLMs reveal substantial performance gaps.
  arXiv  Detail & Related papers  (2025-08-22T13:04:43Z)
• LegalAgentBench: Evaluating LLM Agents in Legal Domain [53.70993264644004]
  LegalAgentBench is a benchmark specifically designed to evaluate LLM Agents in the Chinese legal domain.<n>LegalAgentBench includes 17 corpora from real-world legal scenarios and provides 37 tools for interacting with external knowledge.
  arXiv  Detail & Related papers  (2024-12-23T04:02:46Z)
• AI Adoption to Combat Financial Crime: Study on Natural Language Processing in Adverse Media Screening of Financial Services in English and Bangla multilingual interpretation [0.0]
  This report measures the effectiveness of NLP is promising with an accuracy around 94%.<n>Some AML & CFT concerns are already being addressed by AI technology.<n>This investigation underscores the potential of AI-driven NLP solutions in fortifying efforts to prevent financial crimes in Bangladesh.
  arXiv  Detail & Related papers  (2024-12-12T07:17:05Z)
• Exploring Possibilities of AI-Powered Legal Assistance in Bangladesh through Large Language Modeling [0.0]
  This research seeks to develop a specialized Large Language Model (LLM) to assist in the Bangladeshi legal system. We created UKIL-DB-EN, an English corpus of Bangladeshi legal documents, by collecting and scraping data on various legal acts. We fine-tuned the GPT-2 model on this dataset to develop GPT2-UKIL-EN, an LLM focused on providing legal assistance in English.
  arXiv  Detail & Related papers  (2024-10-22T17:34:59Z)
• InternLM-Law: An Open Source Chinese Legal Large Language Model [72.2589401309848]
  InternLM-Law is a specialized LLM tailored for addressing diverse legal queries related to Chinese laws. We meticulously construct a dataset in the Chinese legal domain, encompassing over 1 million queries. InternLM-Law achieves the highest average performance on LawBench, outperforming state-of-the-art models, including GPT-4, on 13 out of 20 subtasks.
  arXiv  Detail & Related papers  (2024-06-21T06:19:03Z)
• Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models [79.46179534911019]
  Large language models (LLMs) have demonstrated multilingual capabilities, yet they are mostly English-centric due to imbalanced training corpora.<n>We extend the evaluation to real-world user queries and non-English-centric LLMs, offering a broader examination of multilingual performance.
  arXiv  Detail & Related papers  (2024-03-15T12:47:39Z)
• NeCo@ALQAC 2023: Legal Domain Knowledge Acquisition for Low-Resource Languages through Data Enrichment [2.441072488254427]
  This paper presents NeCo Team's solutions to the Vietnamese text processing tasks provided in the Automated Legal Question Answering Competition 2023 (ALQAC 2023) Our methods for the legal document retrieval task employ a combination of similarity ranking and deep learning models, while for the second task, we propose a range of adaptive techniques to handle different question types. Our approaches achieve outstanding results on both tasks of the competition, demonstrating the potential benefits and effectiveness of question answering systems in the legal field.
  arXiv  Detail & Related papers  (2023-09-11T14:43:45Z)
• Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts [75.33019401706188]
  Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars. We propose to assemble synthetic exemplars from a diverse set of high-resource languages to prompt the LLMs to translate from any language into English. Our unsupervised prompting method performs on par with supervised few-shot learning in LLMs of different sizes for translations between English and 13 Indic and 21 African low-resource languages.
  arXiv  Detail & Related papers  (2023-06-20T08:27:47Z)
• Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents [56.40163943394202]
  We release the Longformer-based pre-trained language model, named as Lawformer, for Chinese legal long documents understanding. We evaluate Lawformer on a variety of LegalAI tasks, including judgment prediction, similar case retrieval, legal reading comprehension, and legal question answering.
  arXiv  Detail & Related papers  (2021-05-09T09:39:25Z)
• Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension [86.1617182312817]
  We propose two auxiliary tasks in the fine-tuning stage to create additional phrase boundary supervision. A mixed Machine Reading task, which translates the question or passage to other languages and builds cross-lingual question-passage pairs. A language-agnostic knowledge masking task by leveraging knowledge phrases mined from web.
  arXiv  Detail & Related papers  (2020-04-29T10:44:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.