Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks
This addresses the challenge of efficiently leveraging retrieval for non-knowledge-intensive tasks, which is incremental as it adapts existing retrieval-augmented approaches to a less-studied domain.
The paper tackles the under-explored problem of applying retrieval-augmented methods to non-knowledge-intensive tasks by proposing a two-stage framework (PGRA) that uses a task-agnostic retriever and a prompt-guided reranker, resulting in outperforming state-of-the-art methods.
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. Codes are available at https://github.com/THUNLP-MT/PGRA.