Long-form question answering (LFQA) aims to generate a paragraph-length answer for a given question. While current work on LFQA using large pre-trained model for generation are effective at producing fluent and somewhat relevant content, one primary challenge lies in how to generate a faithful answer that has less hallucinated content. We propose a new end-to-end framework that jointly models answer generation and machine reading. The key idea is to augment the generation model with fine-grained, answer-related salient information which can be viewed as an emphasis on faithful facts. State-of-the-art results on two LFQA datasets, ELI5 and MS MARCO, demonstrate the effectiveness of our method, in comparison with strong baselines on automatic and human evaluation metrics. A detailed analysis further proves the competency of our methods in generating fluent, relevant, and more faithful answers.
@article{arxiv.2203.00343,
title = {Read before Generate! Faithful Long Form Question Answering with Machine Reading},
author = {Dan Su and Xiaoguang Li and Jindi Zhang and Lifeng Shang and Xin Jiang and Qun Liu and Pascale Fung},
journal= {arXiv preprint arXiv:2203.00343},
year = {2022}
}