Read before Generate! Faithful Long Form Question Answering with Machine Reading
Dan Su, Xiaoguang Li, Jindi Zhang, Lifeng Shang, Xin Jiang, Qun Liu, Pascale Fung
Abstract
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.- Anthology ID:
- 2022.findings-acl.61
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2022
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 744–756
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2022.findings-acl.61/
- DOI:
- 10.18653/v1/2022.findings-acl.61
- Cite (ACL):
- Dan Su, Xiaoguang Li, Jindi Zhang, Lifeng Shang, Xin Jiang, Qun Liu, and Pascale Fung. 2022. Read before Generate! Faithful Long Form Question Answering with Machine Reading. In Findings of the Association for Computational Linguistics: ACL 2022, pages 744–756, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Read before Generate! Faithful Long Form Question Answering with Machine Reading (Su et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2022.findings-acl.61.pdf
- Data
- ELI5, HotpotQA, KILT, MS MARCO, Natural Questions