Abstract
In Open-domain Question Answering (ODQA), it is essential to discern relevant contexts as evidence and avoid spurious ones among retrieved results. The model architecture that uses concatenated multiple contexts in the decoding phase, *i.e.*, Fusion-in-Decoder, demonstrates promising performance but generates incorrect outputs from seemingly plausible contexts. To address this problem, we propose the ***M**ulti-**G**ranularity guided **F**usion-**i**n-**D**ecoder (**MGFiD**)*, discerning evidence across multiple levels of granularity. Based on multi-task learning, MGFiD harmonizes passage re-ranking with sentence classification. It aggregates evident sentences into an *anchor vector* that instructs the decoder. Additionally, it improves decoding efficiency by reusing the results of passage re-ranking for *passage pruning*. Through our experiments, MGFiD outperforms existing models on the Natural Questions (NQ) and TriviaQA (TQA) datasets, highlighting the benefits of its multi-granularity solution.- Anthology ID:
- 2024.findings-naacl.142
- Volume:
- Findings of the Association for Computational Linguistics: NAACL 2024
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Kevin Duh, Helena Gomez, Steven Bethard
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2201–2212
- Language:
- URL:
- https://aclanthology.org/2024.findings-naacl.142
- DOI:
- 10.18653/v1/2024.findings-naacl.142
- Cite (ACL):
- Eunseong Choi, Hyeri Lee, and Jongwuk Lee. 2024. Multi-Granularity Guided Fusion-in-Decoder. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 2201–2212, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- Multi-Granularity Guided Fusion-in-Decoder (Choi et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/2024.findings-naacl.142.pdf