SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.17653 · 2023

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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. Codes are available at https://github.com/THUNLP-MT/PGRA.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.17653")
get_code_for_paper("2305.17653")
have("2305.17653")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.17653.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.17653.svg)](https://syntology.ai/paper/2305.17653)

Connect an agent — have() is free.