The paper introduces ChatQA, a conversational question answering model that achieves GPT-4 level accuracies. It proposes a two-stage instruction tuning method and a dense retriever for retrieval in conversational QA. ChatQA-70B outperforms GPT-4 without using synthetic data.

https://arxiv.org/abs//2401.10225

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers