Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks

Zhicheng Guo, Sijie Cheng, Yile Wang, Peng Li, Yang Liu


Abstract
Retrieval-augmented methods have received increasing attention to support downstream tasks by leveraging useful information from external resources. Recent studies mainly focus on exploring retrieval to solve knowledge-intensive (KI) tasks. However, the potential of retrieval for most non-knowledge-intensive (NKI) tasks remains under-explored. There are two main challenges to leveraging retrieval-augmented methods for NKI tasks: 1) the demand for diverse relevance score functions and 2) the dilemma between training cost and task performance. To address these challenges, we propose a two-stage framework for NKI tasks, named PGRA. In the first stage, we adopt a task-agnostic retriever to build a shared static index and select candidate evidence efficiently. In the second stage, we design a prompt-guided reranker to rerank the nearest evidence according to task-specific relevance for the reader. Experimental results show that PGRA outperforms other state-of-the-art retrieval-augmented methods. Our analyses further investigate the influence factors to model performance and demonstrate the generality of PGRA. The code and model will be released for further research.
Anthology ID:
2023.findings-acl.693
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:
10896–10912
Language:
URL:
https://aclanthology.org/2023.findings-acl.693
DOI:
10.18653/v1/2023.findings-acl.693
Bibkey:
Cite (ACL):
Zhicheng Guo, Sijie Cheng, Yile Wang, Peng Li, and Yang Liu. 2023. Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks. In Findings of the Association for Computational Linguistics: ACL 2023, pages 10896–10912, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks (Guo et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.693.pdf