Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Chhabra, Vansh"'
Autor:
Roychowdhury, Sujoy, Soman, Sumit, Ranjani, H G, Gunda, Neeraj, Chhabra, Vansh, Bala, Sai Krishna
Retrieval Augmented Generation (RAG) is widely used to enable Large Language Models (LLMs) perform Question Answering (QA) tasks in various domains. However, RAG based on open-source LLM for specialized domains has challenges of evaluating generated
Externí odkaz:
http://arxiv.org/abs/2407.12873
Autor:
Roychowdhury, Sujoy, Soman, Sumit, Ranjani, H. G., Chhabra, Vansh, Gunda, Neeraj, Gautam, Shashank, Bandyopadhyay, Subhadip, Bala, Sai Krishna
A plethora of sentence embedding models makes it challenging to choose one, especially for technical domains rich with specialized vocabulary. In this work, we domain adapt embeddings using telecom, health and science datasets for question answering.
Externí odkaz:
http://arxiv.org/abs/2406.12336