Abstract
Open-Domain Question Answering (ODQA) systems necessitate a reader model capable of generating answers by simultaneously referring to multiple passages. Although representative models like Fusion-in-Decoder (FiD) have been proposed to address this challenge, these systems can inadvertently rely on spurious features instead of genuine causal relationships between the question and the passages to generate answers. To counter this problem, we introduce the Rational Fusion-in-Decoder (RFiD) model. Our model leverages the encoders of FiD to differentiate between causal relationships and spurious features, subsequently guiding the decoder to generate answers informed by this discernment. Experimental results on two ODQA datasets, Natural Questions (NQ) and TriviaQA (TQ), demonstrate that our model surpasses previous methods, achieving improvements of up to 1.5 and 0.7 in Exact Match scores on NQ, and exhibits an enhanced ability to identify causal relationships.- Anthology ID:
- 2023.findings-acl.155
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2473–2481
- Language:
- URL:
- https://preview.aclanthology.org/remove-affiliations/2023.findings-acl.155/
- DOI:
- 10.18653/v1/2023.findings-acl.155
- Cite (ACL):
- Cunxiang Wang, Haofei Yu, and Yue Zhang. 2023. RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answering. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2473–2481, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answering (Wang et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/remove-affiliations/2023.findings-acl.155.pdf