Top Research Papers on Retrieval Augmented Generation
Dive into the top research papers on Retrieval Augmented Generation, a cutting-edge field at the intersection of information retrieval and natural language generation. This compilation highlights pioneering studies and provides valuable insights for researchers, professionals, and enthusiasts. Enhance your knowledge and stay current with the latest advancements in Retrieval Augmented Generation.
Looking for research-backed answers?Try AI Search
Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers
143 Citations 2024Kunal Sawarkar, Abhilasha Mangal, Shivam R Solanki
IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR)
This paper proposes the ‘Blended RAG’ method of leveraging semantic search techniques, such as Dense Vector indexes and Sparse Encoder indexes, blended with hybrid query strategies, which achieves better retrieval results and sets new benchmarks for IR datasets like NQ and TREC-COVID datasets.
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
172 Citations 2024Yixuan Tang, Yi Yang
ArXiv
A novel dataset, MultiHop-RAG, which consists of a knowledge base, a large collection of multi-hop queries, their ground-truth answers, and the associated supporting evidence, and it is hoped MultiHop-RAG will be a valuable resource for the community in developing effective RAG systems, thereby facilitating greater adoption of LLMs in practice.
The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
102 Citations 2024Shenglai Zeng, Jiankun Zhang, Pengfei He + 8 more
journal unavailable
Shenglai Zeng, Jiankun Zhang, Pengfei He, Yiding Liu, Yue Xing, Han Xu, Jie Ren, Yi Chang, Shuaiqiang Wang, Dawei Yin, Jiliang Tang. Findings of the Association for Computational Linguistics: ACL 2024. 2024.
CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models
104 Citations 2024Yuanjie Lyu, Zhiyu Li, Simin Niu + 7 more
ACM Transactions on Information Systems
This paper constructs a large-scale and more comprehensive benchmark, and evaluates all the components of RAG systems in various RAG application scenarios, and refers to the CRUD actions that describe interactions between users and knowledge bases, and categorizes the range of RAG applications into four distinct types.
Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering
323 Citations 2023Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen + 3 more
Transactions of the Association for Computational Linguistics
This paper proposes RAG-end2end, an extension to RAG that can adapt to a domain- specific knowledge base by updating all components of the external knowledge base during training and introduces an auxiliary training signal to inject more domain-specific knowledge.
CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering
117 Citations 2024Nirmalie Wiratunga, Ramitha Abeyratne, Lasal Jayawardena + 6 more
Lecture notes in computer science
Retrieval-Augmented Generation (RAG) enhances Large Language Model (LLM) output by providing prior knowledge as context to input. This is beneficial for knowledge-intensive and expert reliant tasks, including legal question-answering, which require evidence to validate generated text outputs. We highlight that Case-Based Reasoning (CBR) presents key opportunities to structure retrieval as part of the RAG process in an LLM. We introduce CBR-RAG, where CBR cycle’s initial retrieval stage, its indexing vocabulary, and similarity knowledge containers are used to enhance LLM queries with contextual...
Evaluating Retrieval Quality in Retrieval-Augmented Generation
155 Citations 2024Alireza Salemi, Hamed Zamani
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
Evaluating retrieval-augmented generation with a novel evaluation approach, eRAG, where each document in the retrieval list is individually utilized by the large language model within the RAG system, and the downstream performance for each document serves as its relevance label.
Active Retrieval Augmented Generation
462 Citations 2023Zhengbao Jiang, Frank F. Xu, Luyu Gao + 6 more
Conference on Empirical Methods in Natural Language Processing (EMNLP)
Zhengbao Jiang, Frank Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, Graham Neubig. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
795 Citations 2024Wenqi Fan, Yujuan Ding, Liangbo Ning + 5 more
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
This survey comprehensively review existing research studies in RA-LLMs, covering three primary technical perspectives: architectures, training strategies, and applications, and systematically review mainstream relevant work by their architectures, training strategies, and application areas.
Evaluation of Retrieval-Augmented Generation: A Survey
173 Citations 2025Hao Yu, Aoran Gan, Kai Zhang + 3 more
Communications in computer and information science
This work examines and compares several quantifiable metrics of the Retrieval and Generation components, such as relevance, accuracy, and faithfulness, within the current RAG benchmarks, encompassing the possible output and ground truth pairs.
Benchmarking Retrieval-Augmented Generation for Medicine
299 Citations 2024Guangzhi Xiong, Qiao Jin, Zhiyong Lu + 1 more
journal unavailable
While large language models (LLMs) have achieved state-of-the-art performance on a wide range of medical question answering (QA) tasks, they still face challenges with hallucinations and outdated knowledge.Retrievalaugmented generation (RAG) is a promising solution and has been widely adopted.However, a RAG system can involve multiple flexible components, and there is a lack of best practices regarding the optimal RAG setting for various medical purposes.To systematically evaluate such systems, we propose the Medical Information Retrieval-Augmented Generation Evaluation (MIRAGE), a first-of-it...
A Survey on Retrieval-Augmented Text Generation
254 Citations 2022Huayang Li, Yixuan Su, Deng Cai + 2 more
ArXiv
The generic paradigm of retrieval-augmented generation is highlighted, notable approaches according to different tasks including dialogue response generation, machine translation, and other generation tasks are reviewed and some important directions on top of recent methods are pointed out to facilitate future research.
Retrieval Augmented Code Generation and Summarization
128 Citations 2021Rizwan Parvez, Wasi Uddin Ahmad, Saikat Chakraborty + 2 more
journal unavailable
This work proposes a retrieval augmented framework, REDCODER, that retrieves relevant code or summaries from a retrieval database and provides them as a supplement to code generation or summarization models and conducts experiments and extensive analysis on two benchmark datasets.
Graph Retrieval-Augmented Generation: A Survey
182 Citations 2025Boci Peng, Yun Zhu, Yongchao Liu + 5 more
ACM Transactions on Information Systems
The first comprehensive overview of GraphRAG methodologies is provided, encompassing Graph-Based Indexing, Graph-Guided Retrieval, and Graph-Enhanced Generation, encompassing Graph-Based Indexing, Graph-Guided Retrieval, and Graph-Enhanced Generation.
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
1213 Citations 2023Akari Asai, Zeqiu Wu, Yizhong Wang + 2 more
ArXiv
A new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) is introduced that enhances an LM's quality and factuality through retrieval and self-reflection and shows significant gains in improving factuality and citation accuracy for long-form generations relative to state-of-the-art models.
RAGAs: Automated Evaluation of Retrieval Augmented Generation
537 Citations 2024Shahul Es, Jithin James, Luis Espinosa-Anke + 1 more
journal unavailable
Shahul Es, Jithin James, Luis Espinosa Anke, Steven Schockaert. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations. 2024.
LightRAG: Simple and Fast Retrieval-Augmented Generation
193 Citations 2025Zirui Guo, Lianghao Xia, Yanhua Yu + 2 more
journal unavailable
Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user needs.However, existing RAG systems have significant limitations, including reliance on flat data representations and inadequate contextual awareness, which can lead to fragmented answers that fail to capture complex interdependencies.To address these challenges, we propose Ligh-tRAG, a novel framework that incorporates graph structures into text indexing and retrieval processes.This innovative a...
Searching for Best Practices in Retrieval-Augmented Generation
111 Citations 2024Xiaohua Wang, Zhenhua Wang, Xuan Gao + 11 more
Conference on Empirical Methods in Natural Language Processing (EMNLP)
Xiaohua Wang, Zhenghua Wang, Xuan Gao, Feiran Zhang, Yixin Wu, Zhibo Xu, Tianyuan Shi, Zhengyuan Wang, Shizheng Li, Qi Qian, Ruicheng Yin, Changze Lv, Xiaoqing Zheng, Xuanjing Huang. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
Retrieval-augmented generation for generative artificial intelligence in health care
138 Citations 2025Rui Yang, Yilin Ning, Emilia Keppo + 6 more
npj Health Systems
This work analyzes the possible contributions that RAG could bring to health care in equity, reliability, and personalization, and discusses the current limitations and challenges of implementing RAG in medical scenarios.
Interactive AI With Retrieval-Augmented Generation for Next Generation Networking
143 Citations 2024Ruichen Zhang, Hongyang Du, Yinqiu Liu + 5 more
IEEE Network
This article proposes an IAI-enabled network management and optimization framework, which consists of environment, perception, action, and brain units, and demonstrates through case studies that the IAI framework can effectively perform optimization problem design.
