Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks

Akari Asai, Matt Gardner, Hannaneh Hajishirzi


Abstract
Retrieval-augmented generation models have shown state-of-the-art performance across many knowledge-intensive NLP tasks such as open-domain question answering and fact verification. These models are trained to generate a final output given retrieved passages that can be irrelevant to an input query, leading to learning spurious cues or memorization. This work introduces a method to incorporate evidentiality of passages—whether a passage contains correct evidence to support the output—into training the generator. We introduce a multi-task learning framework to jointly generate the final output and predict the evidentiality of each passage. Furthermore, we introduce a new task-agnostic method for obtaining high-quality silver evidentiality labels, addressing the issues of gold evidentiality labels being unavailable in most domains. Our experiments on five datasets across three knowledge-intensive tasks show that our new evidentiality-guided generator significantly outperforms its direct counterpart on all of them, and advances the state of the art on three of them. Our analysis shows that multi-task learning and silver evidentiality mining play key roles. Our code is available at https://github.com/AkariAsai/evidentiality_qa
Anthology ID:
2022.naacl-main.162
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2226–2243
Language:
URL:
https://aclanthology.org/2022.naacl-main.162
DOI:
10.18653/v1/2022.naacl-main.162
Bibkey:
Cite (ACL):
Akari Asai, Matt Gardner, and Hannaneh Hajishirzi. 2022. Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2226–2243, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks (Asai et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.162.pdf
Code
 akariasai/evidentiality_qa
Data
FEVERFaVIQKILTNatural QuestionsTriviaQAWizard of Wikipedia