mlsanityData to 14 Oct 2026

NepKANUN: A RAG-Based Nepali Legal Assistant

arXiv 2609.15999 ↗First posted 15 Jul 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Accessing legal information in Nepal is difficult due to complex terminology, limited resources, and misinformation. We introduce an AI-powered legal assistant that is tailored for Nepali legal texts and is built on a fine-tuned large language model. The technology provides precise, streamlined answers to natural language legal inquiries when integrated into a Retrieval-Augmented Generation (RAG) framework. It was trained using a custom dataset of high-quality question-answer pairs, and according to BERTScore, it obtained strong F1 scores of 0.82 (simple), 0.77 (moderate), and 0.71 (complex). Its usability is further confirmed by expert reviews. Our method shows how merging generation and retrieval can effectively democratize access to legal knowledge in Nepal by focusing on customized legal data and incorporating RAG.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 25 references that are in the map. First posted on arXiv 15 Jul 2026.

Builds on

14 of 25 references.

References · 14

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  7. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  8. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  9. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  10. 2023A Survey of Large Language Modelscited by 2,576
  11. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  12. 2022Pre-trained Language Models for the Legal Domain: A Case Study on Indian Lawcited by 39
2 more
  1. 2024Domain-adaptative Continual Learning for Low-resource Tasks: Evaluation on Nepalicited by 5
  2. 2024Optimizing Nepali PDF Extraction: A Comparative Study of Parser and OCR Technologiescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Retrieval Augmented Generation Framework for the Nepali Legal Domain Question Answering
  2. 2025LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrieval
  3. 2024LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain
  4. 2025A Reasoning-Focused Legal Retrieval Benchmark
  5. 2026Efficient LLM Distillation for Bangladesh Legal Context: A Smartphone-Compatible Retrieval-Augmented Generation Model
  6. 2025LawPal : A Retrieval Augmented Generation Based System for Enhanced Legal Accessibility in India
  7. 2025Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics
  8. 2026Fine-grained Claim-level RAG Benchmark for Law