Retrieval Augmented Generation Framework for the Nepali Legal Domain Question Answering
On the map: Retrieval-augmented generation → Legal and financial RAG
Abstract (arXiv)
Legal domains in high-resource languages like English have widely adopted artificial intelligence for legal question answering. However, data scarcity in low resource languages such as Nepali has limited the training of large language models on Nepali legal texts. This study presents the first application of a Retrieval Augmented Generation based model for Nepali legal question answering using case laws extracted from the Nepal Kanun Patrika digital archive. Using BM25 on chunked documents, the approach achieved a top precision at one of 91 percent, and up to 75 percent with the multilingual E5 large model. Evaluation of generated answers showed 74 percent groundedness, 85 percent truthfulness according to an automated judge model, and 84 percent human evaluated truthfulness when using BM25 document retrieval, with a 92 percent successful answer generation rate. These results demonstrate that the RAG pipeline can effectively address the gap in legal question answering for low resource languages and provide a foundation for reliable AI systems in the Nepali legal domain.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation. Builds on 17 of its 27 references that are in the map. First posted on arXiv 20 Apr 2026.
Builds on
17 of 27 references.
References · 17
- 2023GPT-4 Technical Reportcited by 18,132
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
- 2020Language-agnostic BERT Sentence Embeddingcited by 621
- 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 357
- 2023R-Tuning: Instructing Large Language Models to Say `I Don't Know'cited by 106
- 2024Evaluating Retrieval Quality in Retrieval-Augmented Generationcited by 90
- 2024Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challengescited by 42
- 2025Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Surveycited by 20
- 2024ConSiDERS-The-Human Evaluation Framework: Rethinking Human Evaluation for Generative Large Language Modelscited by 15
- 2023Explicitly Integrating Judgment Prediction with Legal Document Retrieval: A Law-Guided Generative Approachcited by 14
- 2025GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigationcited by 11
5 more
- 2023Evaluating Factual Consistency of Summaries with Large Language Modelscited by 9
- 2025Assessing the Performance Gap Between Lexical and Semantic Models for Information Retrieval With Formulaic Legal Languagecited by 3
- 2024Vietnamese Legal Information Retrieval in Question-Answering Systemcited by 2
- 2025UQLegalAI@COLIEE2025: Advancing Legal Case Retrieval with Large Language Models and Graph Neural Networkscited by 2
- 2025Evaluating the Retrieval Robustness of Large Language Modelscited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026NepKANUN: A RAG-Based Nepali Legal Assistant
- 2026AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System
- 2025Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics
- 2024CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering
- 2026Fine-grained Claim-level RAG Benchmark for Law
- 2025A Reasoning-Focused Legal Retrieval Benchmark
- 2026Efficient LLM Distillation for Bangladesh Legal Context: A Smartphone-Compatible Retrieval-Augmented Generation Model
- 2026Legal-DC: Benchmarking Retrieval-Augmented Generation for Legal Documents