Unified Active Retrieval for Retrieval Augmented Generation
- URL: http://arxiv.org/abs/2406.12534v4
- Date: Thu, 03 Oct 2024 02:39:56 GMT
- Title: Unified Active Retrieval for Retrieval Augmented Generation
- Authors: Qinyuan Cheng, Xiaonan Li, Shimin Li, Qin Zhu, Zhangyue Yin, Yunfan Shao, Linyang Li, Tianxiang Sun, Hang Yan, Xipeng Qiu,
- Abstract summary: In Retrieval-Augmented Generation (RAG), retrieval is not always helpful and applying it to every instruction is sub-optimal.
Existing active retrieval methods face two challenges: 1.
They usually rely on a single criterion, which struggles with handling various types of instructions.
They depend on specialized and highly differentiated procedures, and thus combining them makes the RAG system more complicated.
- Score: 69.63003043712696
- License:
- Abstract: In Retrieval-Augmented Generation (RAG), retrieval is not always helpful and applying it to every instruction is sub-optimal. Therefore, determining whether to retrieve is crucial for RAG, which is usually referred to as Active Retrieval. However, existing active retrieval methods face two challenges: 1. They usually rely on a single criterion, which struggles with handling various types of instructions. 2. They depend on specialized and highly differentiated procedures, and thus combining them makes the RAG system more complicated and leads to higher response latency. To address these challenges, we propose Unified Active Retrieval (UAR). UAR contains four orthogonal criteria and casts them into plug-and-play classification tasks, which achieves multifaceted retrieval timing judgements with negligible extra inference cost. We further introduce the Unified Active Retrieval Criteria (UAR-Criteria), designed to process diverse active retrieval scenarios through a standardized procedure. Experiments on four representative types of user instructions show that UAR significantly outperforms existing work on the retrieval timing judgement and the performance of downstream tasks, which shows the effectiveness of UAR and its helpfulness to downstream tasks.
Related papers
- HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks [50.871243190126826]
HawkBench is a human-labeled, multi-domain benchmark designed to rigorously assess RAG performance.
By stratifying tasks based on information-seeking behaviors, HawkBench provides a systematic evaluation of how well RAG systems adapt to diverse user needs.
arXiv Detail & Related papers (2025-02-19T06:33:39Z) - Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control [52.405085773954596]
Retrieval-Augmented Generation (RAG) has emerged as a powerful approach to mitigate large language model hallucinations.
Existing RAG frameworks often apply retrieval indiscriminately,leading to inefficiencies-over-retrieving.
We introduce a novel user-controllable RAG framework that enables dynamic adjustment of the accuracy-cost trade-off.
arXiv Detail & Related papers (2025-02-17T18:56:20Z) - Chain-of-Retrieval Augmented Generation [72.06205327186069]
This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.
Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
arXiv Detail & Related papers (2025-01-24T09:12:52Z) - Unanswerability Evaluation for Retrieval Augmented Generation [74.3022365715597]
UAEval4RAG is a framework designed to evaluate whether RAG systems can handle unanswerable queries effectively.
We define a taxonomy with six unanswerable categories, and UAEval4RAG automatically synthesizes diverse and challenging queries.
arXiv Detail & Related papers (2024-12-16T19:11:55Z) - MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity [30.346398341996476]
We propose a reinforcement learning-based framework that dynamically selects the most suitable retrieval strategy based on query complexity.
Our method achieves new state of the art results on multiple single-hop and multi-hop datasets while reducing retrieval costs.
arXiv Detail & Related papers (2024-12-02T14:55:02Z) - Self-adaptive Multimodal Retrieval-Augmented Generation [0.0]
We propose a new approach called Self-adaptive Multimodal Retrieval-Augmented Generation (SAM-RAG)
SAM-RAG not only dynamically filters relevant documents based on the input query, including image captions when needed, but also verifies the quality of both the retrieved documents and the output.
Extensive experimental results show that SAM-RAG surpasses existing state-of-the-art methods in both retrieval accuracy and response generation.
arXiv Detail & Related papers (2024-10-15T06:39:35Z) - Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach [6.549143816134531]
We propose a novel iterative RAG method called ReSP, equipped with a dual-function summarizer.
Experimental results on the multi-hop question-answering HotpotQA and 2WikiMultihopQA demonstrate that our method significantly outperforms the state-of-the-art.
arXiv Detail & Related papers (2024-07-18T02:19:00Z) - AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment [16.62505706601199]
We present a novel framework AdaCQR for conversational search reformulation.
By aligning reformulation models with both term-based and semantic-based retrieval systems, AdaCQR enhances the generalizability of information-seeking queries.
Experimental results on the TopiOCQA and QReCC datasets demonstrate that AdaCQR outperforms the existing methods in a more efficient framework.
arXiv Detail & Related papers (2024-07-02T05:50:16Z) - ReAct: Temporal Action Detection with Relational Queries [84.76646044604055]
This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries.
We first propose a relational attention mechanism in the decoder, which guides the attention among queries based on their relations.
Lastly, we propose to predict the localization quality of each action query at inference in order to distinguish high-quality queries.
arXiv Detail & Related papers (2022-07-14T17:46:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.