paper-with-me

Papers

KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generation

2025-02-25 · Jinyuan Fang, Zaiqiao Meng, Craig Macdonald

Iterative retrieval-augmented generation (iRAG) models offer an effective approach for multi-hop question answering (QA). However, their retrieval process faces two key challenges: (1) it can be disrupted by irrelevant documents or factually inaccurate chain-of-thoughts; (2) their retrievers are not designed to dynamically adapt to the evolving information needs in multi-step reasoning, making it difficult to identify and retrieve the missing information required at each iterative step. Therefore, we propose KiRAG, which uses a knowledge-driven iterative retriever model to enhance the retrieval process of iRAG. Specifically, KiRAG decomposes documents into knowledge triples and performs iterative retrieval with these triples to enable a factually reliable retrieval process. Moreover, KiRAG integrates reasoning into the retrieval process to dynamically identify and retrieve knowledge that bridges information gaps, effectively adapting to the evolving information needs. Empirical results show that KiRAG significantly outperforms existing iRAG models, with an average improvement of 9.40% in R@3 and 5.14% in F1 on multi-hop QA.

📄 PDF Abstract BibTeX arXiv:2502.18397

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-hop Question AnsweringQuestion AnsweringRetrievalRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models

2024-11-29 · Tian Yu, Shaolei Zhang, Yang Feng

Iterative retrieval refers to the process in which the model continuously queries the retriever during generation to enhance the relevance of the retrieved knowledge, thereby improving the performance of Retrieval-Augmen…

Decision MakingRAGRetrievalRetrieval-augmented Generation

Accelerating Retrieval-Augmented Language Model Serving with Speculation

2024-01-25 · Zhihao Zhang, Alan Zhu, Lijie Yang, Yihua Xu 외

Retrieval-augmented language models (RaLM) have demonstrated the potential to solve knowledge-intensive natural language processing (NLP) tasks by combining a non-parametric knowledge base with a parametric language mode…

Language ModelingLanguage ModellingmodelRetrieval

Retriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented Generation

2024-10-11 · Ruobing Wang, Daren Zha, Shi Yu, Qingfei Zhao 외

Retrieval-Augmented Generation (RAG) mitigates issues of the factual errors and hallucinated outputs generated by Large Language Models (LLMs) in open-domain question-answering tasks (OpenQA) via introducing external kno…

Open-Domain Question AnsweringQuestion AnsweringRAGRetrieval+1

Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling

2024-03-06 · Chao-Wei Huang, Chen-An Li, Tsu-Yuan Hsu, Chen-Yu Hsu 외

Dense retrieval methods have demonstrated promising performance in multilingual information retrieval, where queries and documents can be in different languages. However, dense retrievers typically require a substantial …

Information RetrievalRetrieval

BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers

2024-04-29 · ran Xu, Wenqi Shi, Yue Yu, Yuchen Zhuang 외

Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedical tasks but still challenging due to the deficiency of sufficient publicly annotated biomedical data and computa…

RetrievalUnsupervised Pre-training