Tag
MOTHRAG is a multi-hop RAG system that matches the performance of top GPU-dependent systems (HippoRAG 2, CoRAG, NeocorRAG) using only commodity API calls, with no GPU, no fine-tuning, and deployment via pip install plus API keys.
This paper presents Eskwai for Students, a generative AI assistant for legal education in Ghana, using retrieval-augmented generation on a database of over 12K case laws and 1.4K legislation. Deployed in a 30-month study with 3.1K law students, it provides insights into AI usage in legal education in the Global South.
Blue J demonstrates how to scale AI expertise in complex regulated domains by combining GPT-4.1 with retrieval-augmented generation over curated tax documents, achieving <0.14% error rates and 70% weekly user engagement through rigorous feedback loops and domain-specific optimization.