ChatQA: Surpassing GPT-4 on Conversational QA and RAG

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Zihan, Ping, Wei, Roy, Rajarshi, Xu, Peng, Lee, Chankyu, Shoeybi, Mohammad, Catanzaro, Bryan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929567795511296
author Liu, Zihan
Ping, Wei
Roy, Rajarshi
Xu, Peng
Lee, Chankyu
Shoeybi, Mohammad
Catanzaro, Bryan
author_facet Liu, Zihan
Ping, Wei
Roy, Rajarshi
Xu, Peng
Lee, Chankyu
Shoeybi, Mohammad
Catanzaro, Bryan
contents In this work, we introduce ChatQA, a suite of models that outperform GPT-4 on retrieval-augmented generation (RAG) and conversational question answering (QA). To enhance generation, we propose a two-stage instruction tuning method that significantly boosts the performance of RAG. For effective retrieval, we introduce a dense retriever optimized for conversational QA, which yields results comparable to the alternative state-of-the-art query rewriting models, while substantially reducing deployment costs. We also present the ChatRAG Bench, which encompasses ten datasets covering comprehensive evaluations on RAG, table-related QA, arithmetic calculations, and scenarios involving unanswerable questions. Our ChatQA-1.0-70B (score: 54.14), built on Llama2, a weaker foundation model than GPT-4, can slightly outperform GPT-4-0613 (score: 53.90) and GPT-4-Turbo-2024-04-09 (score: 54.03) on the ChatRAG Bench, without relying on any synthetic data from OpenAI GPT models. Notably, the Llama3-ChatQA-1.5-70B model surpasses the accuracy of GPT-4-Turbo-2024-04-09, achieving a 4.4% improvement. To advance research in this field, we open-sourced the model weights, instruction tuning data, ChatRAG Bench, and retriever for the community: https://chatqa-project.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10225
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ChatQA: Surpassing GPT-4 on Conversational QA and RAG
Liu, Zihan
Ping, Wei
Roy, Rajarshi
Xu, Peng
Lee, Chankyu
Shoeybi, Mohammad
Catanzaro, Bryan
Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
In this work, we introduce ChatQA, a suite of models that outperform GPT-4 on retrieval-augmented generation (RAG) and conversational question answering (QA). To enhance generation, we propose a two-stage instruction tuning method that significantly boosts the performance of RAG. For effective retrieval, we introduce a dense retriever optimized for conversational QA, which yields results comparable to the alternative state-of-the-art query rewriting models, while substantially reducing deployment costs. We also present the ChatRAG Bench, which encompasses ten datasets covering comprehensive evaluations on RAG, table-related QA, arithmetic calculations, and scenarios involving unanswerable questions. Our ChatQA-1.0-70B (score: 54.14), built on Llama2, a weaker foundation model than GPT-4, can slightly outperform GPT-4-0613 (score: 53.90) and GPT-4-Turbo-2024-04-09 (score: 54.03) on the ChatRAG Bench, without relying on any synthetic data from OpenAI GPT models. Notably, the Llama3-ChatQA-1.5-70B model surpasses the accuracy of GPT-4-Turbo-2024-04-09, achieving a 4.4% improvement. To advance research in this field, we open-sourced the model weights, instruction tuning data, ChatRAG Bench, and retriever for the community: https://chatqa-project.github.io/.
title ChatQA: Surpassing GPT-4 on Conversational QA and RAG
topic Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2401.10225