1 citations · 1 across the 4 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.AI2025
Lightweight Relevance Grader in RAG
Taehee Jeong
Retrieval-Augmented Generation (RAG) addresses limitations of large language models (LLMs) by leveraging a vector database to provide more accurate and up-to-date information. When…
cs.LG2025
4bit-Quantization in Vector-Embedding for RAG
Taehee Jeong
Retrieval-augmented generation (RAG) is a promising technique that has shown great potential in addressing some of the limitations of large language models (LLMs). LLMs have two ma…