{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:19:39Z","timestamp":1783153179885,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62306138"],"award-info":[{"award-number":["62306138"]}]},{"name":"Jiangsu Natural Science Foundation","award":["BK20230784"],"award-info":[{"award-number":["BK20230784"]}]},{"name":"Innovation Program of the State Key Laboratory for Novel Software Technology, Nanjing University","award":["ZZKT2024B15&#x3b; ZZKT2025B25"],"award-info":[{"award-number":["ZZKT2024B15&#x3b; ZZKT2025B25"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792512","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"2240-2251","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2736-0026","authenticated-orcid":false,"given":"Hao","family":"Yang","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing University, Suzhou, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1722-1236","authenticated-orcid":false,"given":"Zhiyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2382-7617","authenticated-orcid":false,"given":"Xupeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Isoftstone Information Technology (Group) Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3916-1249","authenticated-orcid":false,"given":"Wei","family":"Wei","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4502-2106","authenticated-orcid":false,"given":"Yunjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic Information, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9056-0500","authenticated-orcid":false,"given":"Lin","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Suzhou, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AI@Meta. 2024. Llama 3 Model Card. (2024). https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"e_1_3_2_1_2_1","volume-title":"International conference on machine learning. PMLR, 2206-2240","author":"Borgeaud Sebastian","year":"2022","unstructured":"Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George Bm Van Den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, et al., 2022. Improving language models by retrieving from trillions of tokens. In International conference on machine learning. PMLR, 2206-2240."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1539"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Hyung Won Chung and othrs. 2022. Scaling Instruction-Finetuned Language Models. doi:10.48550\/ARXIV.2210.11416","DOI":"10.48550\/ARXIV.2210.11416"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.496"},{"key":"e_1_3_2_1_6_1","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yi Dai Jiawei Sun Meng Wang and Haofen Wang. 2024. Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv:2312.10997 [cs.CL] https:\/\/arxiv.org\/abs\/2312.10997"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.148"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","unstructured":"Wangzhen Guo Qinkang Gong Yanghui Rao and Hanjiang Lai. 2023. Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Anna Rogers Jordan Boyd-Graber and Naoaki Okazaki (Eds.). Association for Computational Linguistics Toronto Canada 4214-4226. doi:10.18653\/v1\/2023.acl-long.231","DOI":"10.18653\/v1\/2023.acl-long.231"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.580"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","unstructured":"Gautier Izacard Mathilde Caron Lucas Hosseini Sebastian Riedel Piotr Bojanowski Armand Joulin and Edouard Grave. 2021. Unsupervised Dense Information Retrieval with Contrastive Learning. doi:10.48550\/ARXIV.2112.09118","DOI":"10.48550\/ARXIV.2112.09118"},{"key":"e_1_3_2_1_11_1","article-title":"Atlas: few-shot learning with retrieval augmented language models","volume":"24","author":"Izacard Gautier","year":"2023","unstructured":"Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2023. Atlas: few-shot learning with retrieval augmented language models. J. Mach. Learn. Res., Vol. 24, 1, Article 251 (Jan. 2023), 43 pages.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_12_1","unstructured":"Yuelyu Ji Rui Meng Zhuochun Li and Daqing He. 2025. Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation. arXiv:2505.17391 [cs.CL] https:\/\/arxiv.org\/abs\/2505.17391"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","first-page":"59532","DOI":"10.52202\/079017-1902","article-title":"Hipporag: Neurobiologically inspired long-term memory for large language models","volume":"37","author":"Gutierrez Bernal Jimenez","year":"2024","unstructured":"Bernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. 2024. Hipporag: Neurobiologically inspired long-term memory for large language models. Advances in Neural Information Processing Systems, Vol. 37 (2024), 59532-59569.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","unstructured":"Yiqiao Jin Kartik Sharma Vineeth Rakesh Yingtong Dou Menghai Pan Mahashweta Das and Srijan Kumar. 2025. SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression. In ES-FoMo III: 3rd Workshop on Efficient Systems for Foundation Models. https:\/\/openreview.net\/forum?id=7qSlrCYtTl"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3496517"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 38th International Conference on Neural Information Processing Systems","author":"Li Ruosen","year":"2025","unstructured":"Ruosen Li, Zimu Wang, Son Quoc Tran, Lei Xia, and Xinya Du. 2025. MEQA: a benchmark for multi-hop event-centric question answering with explanations. In Proceedings of the 38th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS '24). Curran Associates Inc., Red Hook, NY, USA, Article 4028, 28 pages."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.97"},{"key":"e_1_3_2_1_20_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR, Vol. abs\/1907.11692 (2019). arXiv:1907.11692 http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_1_21_1","unstructured":"Man Luo Xin Xu Zhuyun Dai Panupong Pasupat Mehran Kazemi Chitta Baral Vaiva Imbrasaite and Vincent Y Zhao. 2023. Dr.ICL: Demonstration-Retrieved In-context Learning. arXiv:2305.14128 [cs.CL] https:\/\/arxiv.org\/abs\/2305.14128"},{"key":"e_1_3_2_1_22_1","unstructured":"OpenAI et al. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_23_1","volume-title":"Kyunghyun Cho, and Douwe Kiela.","author":"Perez Ethan","year":"2020","unstructured":"Ethan Perez, Patrick Lewis, Wen tau Yih, Kyunghyun Cho, and Douwe Kiela. 2020. Unsupervised Question Decomposition for Question Answering. arXiv:2002.09758 [cs.CL] https:\/\/arxiv.org\/abs\/2002.09758"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.378"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.236"},{"key":"e_1_3_2_1_26_1","volume-title":"Aditya Shingote, Aadi Krishna Vikram, Vinija Jain, Aman Chadha, Amit Sheth, and Amitava Das.","author":"Rawte Vipula","year":"2025","unstructured":"Vipula Rawte, Rajarshi Roy, Gurpreet Singh, Danush Khanna, Yaswanth Narsupalli, Basab Ghosh, Abhay Gupta, Argha Kamal Samanta, Aditya Shingote, Aadi Krishna Vikram, Vinija Jain, Aman Chadha, Amit Sheth, and Amitava Das. 2025. RADIANT: Retrieval AugmenteD entIty-context AligNmenT - Introducing RAG-ability and Entity-Context Divergence. arXiv:2507.02949 [cs.CL] https:\/\/arxiv.org\/abs\/2507.02949"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/make7030074"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.620"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679722"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.397"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","unstructured":"Weihang Su Yichen Tang Qingyao Ai Zhijing Wu and Yiqun Liu. 2024. DRAGIN: Dynamic Retrieval Augmented Generation based on the Real-time Information Needs of Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Lun-Wei Ku Andre Martins and Vivek Srikumar (Eds.). Association for Computational Linguistics Bangkok Thailand 12991-13013. doi:10.18653\/v1\/2024.acl-long.702","DOI":"10.18653\/v1\/2024.acl-long.702"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.337"},{"key":"e_1_3_2_1_33_1","unstructured":"Yixuan Tang and Yi Yang. 2024. MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries. arXiv:2401.15391 [cs.CL]"},{"key":"e_1_3_2_1_34_1","volume-title":"MuSiQue: Multihop Questions via Single-hop Question Composition. Transactions of the Association for Computational Linguistics","author":"Trivedi Harsh","year":"2022","unstructured":"Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022. MuSiQue: Multihop Questions via Single-hop Question Composition. Transactions of the Association for Computational Linguistics (2022)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.557"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3602070"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1312"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.871"},{"key":"e_1_3_2_1_40_1","unstructured":"Zhuocheng Zhang Yang Feng and Min Zhang. 2025. LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers. arXiv:2502.18139 [cs.CL] https:\/\/arxiv.org\/abs\/2502.18139"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.971"},{"key":"e_1_3_2_1_42_1","unstructured":"Rongzhi Zhu Xiangyu Liu Zequn Sun Yiwei Wang and Wei Hu. 2025. Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering. In ACL."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.199"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:57:36Z","timestamp":1783151856000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792512"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":43,"alternative-id":["10.1145\/3774904.3792512","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792512","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}