Two research papers introduce AI-powered legal assistants for Nepal, aiming to improve access to justice. The first, NepKANUN, utilizes a retrieval-augmented generation (RAG) framework with a fine-tuned large language model, achieving strong F1 scores on question-answering tasks. The second, NepLEGiT, presents a specialized small language model (SLM) based on GPT-2, pre-trained on a substantial corpus of Nepali legal texts and demonstrating competitive perplexity and prediction accuracy. AI
IMPACT These specialized models demonstrate the potential for AI to democratize access to legal information in underserved regions.
RANK_REASON Two academic papers detailing novel AI models for a specific domain and region.
- arXiv
- BERTScore
- GPT-2
- Hugging Face
- multilingual-BERT
- Nepal
- NepKANUN
- NepLEGiT
- retrieval-augmented generation
- transformer
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →