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

2023-05-28 · Zhicheng Guo, Sijie Cheng, Yile Wang, Peng Li, Yang Liu

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.

📄 PDF Abstract BibTeX arXiv:2305.17653

Code (1)

thunlp-mt/pgra 공식 구현 pytorch

Tasks

Retrieval

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries

2025-02-23 · Yin Wu, Quanyu Long, Jing Li, Jianfei Yu 외

Retrieval-Augmented Generation (RAG) is a popular approach for enhancing Large Language Models (LLMs) by addressing their limitations in verifying facts and answering knowledge-intensive questions. As the research in LLM…

Benchmarking Image Retrieval Question Answering RAG+2

Decoupled Mixture-of-Experts for Parametric Knowledge Injection

2026-06-12 · Baoqing Yue, Weihang Su, Qingyao Ai, Yichen Tang 외 arxiv

Knowledge injection aims to equip large language models (LLMs) with external, domain-specific, or time-sensitive knowledge. Existing approaches typically face a trade-off between flexibility and integration: retrieval-au…

Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks

2024-10-02 · Xingxuan Li, Weiwen Xu, Ruochen Zhao, Fangkai Jiao 외

State-of-the-art large language models (LLMs) exhibit impressive problem-solving capabilities but may struggle with complex reasoning and factual correctness. Existing methods harness the strengths of chain-of-thought an…

Math Navigate RAG Retrieval+1

ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion

2024-01-04 · Shangyu Wu, Ying Xiong, Yufei Cui, Xue Liu 외

Retrieval-based augmentations (RA) incorporating knowledge from an external database into language models have greatly succeeded in various knowledge-intensive (KI) tasks. However, integrating retrievals in non-knowledge…

Natural Language Understanding Neural Architecture Search Question Answering Retrieval+3

Multi-Modal Retrieval Augmentation for Open-Ended and Knowledge-Intensive Video Question Answering

2025-02-17 · Md Zarif Ul Alam, Hamed Zamani

While current video question answering systems perform well on some tasks requiring only direct visual understanding, they struggle with questions demanding knowledge beyond what is immediately observable in the video co…

Multiple-choice Question Answering Retrieval Retrieval-augmented Generation+2