Continually Improving Extractive QA via Human Feedback

Ge Gao; Hung-Ting Chen; Yoav Artzi; Eunsol Choi

EMNLP 2023long main0 citations

Continually Improving Extractive QA via Human Feedback

Ge Gao, Hung-Ting Chen, Yoav Artzi, Eunsol Choi

Abstract

We study continually improving an extractive question answering (QA) system via human user feedback. We design and deploy an iterative approach, where information-seeking users ask questions, receive model-predicted answers, and provide feedback. We conduct experiments involving thousands of user interactions under diverse setups to broaden the understanding of learning from feedback over time. Our experiments show effective improvement from user feedback of extractive QA models over time across different data regimes, including significant potential for domain adaptation.

QAhuman feedbackbandit learning

BibTeX

@inproceedings{
gao2023continually,
title={Continually Improving Extractive {QA} via Human Feedback},
author={Ge Gao and Hung-Ting Chen and Yoav Artzi and Eunsol Choi},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=xNzu8DivUj}
}