{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T23:00:11Z","timestamp":1778540411828,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","funder":[{"name":"the National Natural Science Foundation of China award","award":["62272467"],"award-info":[{"award-number":["62272467"]}]},{"name":"Beijing Natural Science Foundation award","award":["L233008"],"award-info":[{"award-number":["L233008"]}]},{"name":"Beijing Municipal Science and Technology Project award","award":["Z231100010323009"],"award-info":[{"award-number":["Z231100010323009"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,8]]},"DOI":"10.1145\/3701716.3715313","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T14:24:42Z","timestamp":1750688682000},"page":"737-740","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4808-1534","authenticated-orcid":false,"given":"Jiajie","family":"Jin","sequence":"first","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9432-3251","authenticated-orcid":false,"given":"Yutao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9781-948X","authenticated-orcid":false,"given":"Zhicheng","family":"Dou","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2318-0281","authenticated-orcid":false,"given":"Guanting","family":"Dong","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9118-6606","authenticated-orcid":false,"given":"Xinyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8399-2258","authenticated-orcid":false,"given":"Chenghao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9460-2293","authenticated-orcid":false,"given":"Tong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8954-8627","authenticated-orcid":false,"given":"Zhao","family":"Yang","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9777-9676","authenticated-orcid":false,"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[{"name":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"A. Asai Z. Wu Y. Wang A. Sil and H. Hajishirzi. 2023. Self-RAG: Learning to Retrieve Generate and Critique through Self-Reflection. ArXiv preprint (2023)."},{"key":"e_1_3_2_2_2_1","volume-title":"Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation. ArXiv preprint","author":"Fang J.","year":"2024","unstructured":"J. Fang, Z. Meng, and C. Macdonald. 2024. TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation. ArXiv preprint (2024)."},{"key":"e_1_3_2_2_3_1","unstructured":"Z. Feng X. Feng D. Zhao M. Yang and B. Qin. 2023. Retrieval-Generation Synergy Augmented Large Language Models. ArXiv preprint (2023)."},{"key":"e_1_3_2_2_4_1","unstructured":"Y. Gao Y. Xiong X. Gao K. Jia J. Pan Y. Bi Y. Dai J. Sun M. Wang and H. Wang. 2023. Retrieval-Augmented Generation for Large Language Models: A Survey. ArXiv preprint (2023)."},{"key":"e_1_3_2_2_5_1","volume-title":"REALM: Retrieval-Augmented Language Model Pre-Training. ArXiv preprint","author":"Guu K.","year":"2020","unstructured":"K. Guu, K. Lee, Z. Tung, P. Pasupat, and M.-W. Chang. 2020. REALM: Retrieval-Augmented Language Model Pre-Training. ArXiv preprint (2020)."},{"key":"e_1_3_2_2_6_1","unstructured":"P. Izsak M. Berchansky D. Fleischer and R. Laperdon. 20f. fastRAG: Efficient Retrieval Augmentation and Generation Framework. ArXiv preprint (20f)."},{"key":"e_1_3_2_2_7_1","volume":"202","author":"Jeong S.","unstructured":"S. Jeong, J. Baek, S. Cho, S. Hwang, and J. Park. 2024. Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity. In Proc. of NAACL-HLT.","journal-title":"J. Park."},{"key":"e_1_3_2_2_8_1","volume-title":"Proc. of EMNLP.","author":"Jiang H.","unstructured":"H. Jiang, Q. Wu, C.-Y. Lin, Y. Yang, and L. Qiu. 2023a. LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models. In Proc. of EMNLP."},{"key":"e_1_3_2_2_9_1","unstructured":"H. Jiang Q. Wu X. Luo D. Li C.-Y. Lin Y. Yang and L. Qiu. 2023b. LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenario. ArXiv preprint (2023)."},{"key":"e_1_3_2_2_10_1","volume-title":"Proc. of EMNLP.","author":"Jiang Z.","unstructured":"Z. Jiang, F. Xu, L. Gao, Z. Sun, Q. Liu, J. Dwivedi-Yu, Y. Yang, J. Callan, and G. Neubig. 2023c. Active Retrieval Augmented Generation. In Proc. of EMNLP."},{"key":"e_1_3_2_2_11_1","unstructured":"D. Kim B. Kim D. Han and M. Eibich. 2024a. AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipeline. ArXiv preprint (2024)."},{"key":"e_1_3_2_2_12_1","volume":"2024","author":"Kim J.","unstructured":"J. Kim, J. Nam, S. Mo, J. Park, S.-W. Lee, M. Seo, J.-W. Ha, and J. Shin. 2024b. SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs. In Proc. of ICLR.","journal-title":"J. Shin."},{"key":"e_1_3_2_2_13_1","volume-title":"Proc. of SOSP.","author":"Kwon W.","unstructured":"W. Kwon, Z. Li, S. Zhuang, Y. Sheng, L. Zheng, C. H. Yu, J. Gonzalez, H. Zhang, and I. Stoica. 2023. Efficient Memory Management for Large Language Model Serving with PagedAttention. In Proc. of SOSP."},{"key":"e_1_3_2_2_14_1","volume-title":"Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering. ArXiv preprint","author":"Li Y.","year":"2023","unstructured":"Y. Li. 2023. Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering. ArXiv preprint (2023)."},{"key":"e_1_3_2_2_15_1","volume-title":"Proc. of SIGIR.","author":"Lin J.","unstructured":"J. Lin, X. Ma, S.-C. Lin, J.-H. Yang, R. Pradeep, and R. F. Nogueira. 2021. Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations. In Proc. of SIGIR."},{"key":"e_1_3_2_2_16_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. In Proc. of NeurIPS Workshop)","author":"Nguyen T.","year":"2016","unstructured":"T. Nguyen, M. Rosenberg, X. Song, J. Gao, S. Tiwary, R. Majumder, and L. Deng. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. In Proc. of NeurIPS Workshop), Barcelona, Spain, December 9, 2016 (CEUR Workshop Proceedings)."},{"key":"e_1_3_2_2_17_1","unstructured":"M. Pietsch T. M\u00f6ller B. Kostic J. Risch M. Pippi M. Jobanputra S. Zanzottera S. Cerza V. Blagojevic T. Stadelmann T. Soni and S. Lee. 2019. Haystack: the end-to-end NLP framework for pragmatic builders."},{"key":"e_1_3_2_2_18_1","volume-title":"Proc. of ICML (Proceedings of Machine Learning Research).","author":"Radford A.","unstructured":"A. Radford, J. Wook Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, G. Krueger, and I. Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proc. of ICML (Proceedings of Machine Learning Research)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"S. E. Robertson and H. Zaragoza. 2009. The Probabilistic Relevance Framework: BM25 and Beyond. Found. Trends Inf. Retr. 4 (2009).","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_2_20_1","volume-title":"Proc. of EMNLP 2023 Findings.","author":"Shao Z.","unstructured":"Z. Shao, Y. Gong, Y. Shen, M. Huang, N. Duan, and W. Chen. 2023. Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy. In Proc. of EMNLP 2023 Findings."},{"key":"e_1_3_2_2_21_1","volume-title":"Proc. of NAACL-HLT.","author":"Shi W.","unstructured":"W. Shi, S. Min, M. Yasunaga, M. Seo, R. James, M. Lewis, L. Zettlemoyer, and W. Yih. 2024. REPLUG: Retrieval-Augmented Black-Box Language Models. In Proc. of NAACL-HLT."},{"key":"e_1_3_2_2_22_1","volume-title":"Proc. of ACL.","author":"Trivedi H.","unstructured":"H. Trivedi, N. Balasubramanian, T. Khot, and A. Sabharwal. 2023. Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions. In Proc. of ACL."},{"key":"e_1_3_2_2_23_1","volume-title":"Proc. of EMNLP 2023 Findings.","author":"Wang Y.","unstructured":"Y. Wang, P. Li, M. Sun, and Y. Liu. 2023. Self-Knowledge Guided Retrieval Augmentation for Large Language Models. In Proc. of EMNLP 2023 Findings."},{"key":"e_1_3_2_2_24_1","volume-title":"Proc. of EMNLP.","author":"Wolf T.","unstructured":"T. Wolf, L. Debut, V. Sanh, J. Chaumond, C. Delangue, A. Moi, P. Cistac, T. Rault, R. Louf, M. Funtowicz, J. Davison, S. Shleifer, P. von Platen, C. Ma, Y. Jernite, J. Plu, C. Xu, T. Le Scao, S. Gugger, M. Drame, Q. Lhoest, and A. Rush. 2020. Transformers: State-of-the-Art Natural Language Processing. In Proc. of EMNLP."},{"key":"e_1_3_2_2_25_1","volume-title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation. ArXiv preprint","author":"Xu F.","year":"2023","unstructured":"F. Xu, W. Shi, and E. Choi. 2023. RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation. ArXiv preprint (2023)."},{"key":"e_1_3_2_2_26_1","volume":"202","author":"Yoran O.","unstructured":"O. Yoran, T. Wolfson, O. Ram, and J. Berant. 2023. Making Retrieval-Augmented Language Models Robust to Irrelevant Context. ArXiv preprint (2023).","journal-title":"J. Berant."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"X. Yu Y. Lu and Z. Yu. 2024. LocalRQA: From Generating Data to Locally Training Testing and Deployin. ArXiv preprint (2024).","DOI":"10.18653\/v1\/2024.acl-demos.14"},{"key":"e_1_3_2_2_28_1","volume-title":"Proc. of ACL.","author":"Yu Z.","unstructured":"Z. Yu, C. Xiong, S. Yu, and Z. Liu. 2023. Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In. In Proc. of ACL."},{"key":"e_1_3_2_2_29_1","volume-title":"Proc. of the EMNLP: Demo, Delia Irazu Hernandez Farias, Tom Hope, and Manling Li (Eds.).","author":"Zhang X.","unstructured":"X. Zhang, Y. Song, Y. Wang, S. Tang, X. Li, Z. Zeng, Z. Wu, W. Ye, W. Xu, Y. Zhang, X. Dai, S. Zhang, and Q. Wen. 2024. RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation. In Proc. of the EMNLP: Demo, Delia Irazu Hernandez Farias, Tom Hope, and Manling Li (Eds.)."},{"key":"e_1_3_2_2_30_1","volume-title":"Proc. of NeurIPS.","author":"Zheng L.","unstructured":"L. Zheng, W.-L. Chiang, Y. Sheng, S. Zhuang, Z. Wu, Y. Zhuang, Z. Lin, Z. Li, D. Li, E. P. Xing, H. Zhang, J. E. Gonzalez, and I. Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. In Proc. of NeurIPS."},{"key":"e_1_3_2_2_31_1","volume-title":"One Token Can Help! Learning Scalable and Pluggable Virtual Token. ArXiv preprint","author":"Zhu Y.","year":"2024","unstructured":"Y. Zhu, Z. Huang, Z. Dou, and J.-R. Wen. 2024. One Token Can Help! Learning Scalable and Pluggable Virtual Token. ArXiv preprint (2024)."}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701716.3715313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T18:29:24Z","timestamp":1759861764000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3715313"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,8]]},"references-count":31,"alternative-id":["10.1145\/3701716.3715313","10.1145\/3701716"],"URL":"https:\/\/doi.org\/10.1145\/3701716.3715313","relation":{},"subject":[],"published":{"date-parts":[[2025,5,8]]},"assertion":[{"value":"2025-05-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}