{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:30:20Z","timestamp":1772724620648,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657923","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2641-2646","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0800-3340","authenticated-orcid":false,"given":"Hamed","family":"Zamani","sequence":"first","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2941-6240","authenticated-orcid":false,"given":"Michael","family":"Bendersky","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614901"},{"key":"e_1_3_2_1_2_1","unstructured":"Payal Bajaj Daniel Campos Nick Craswell Li Deng Jianfeng Gao Xiaodong Liu Rangan Majumder Andrew McNamara Bhaskar Mitra Tri Nguyen et al. 2016. Ms marco: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 (2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-aacl.10"},{"key":"e_1_3_2_1_4_1","volume-title":"Autoregressive Search Engines: Generating Substrings as Document Identifiers. arXiv preprint arXiv:2204.10628","author":"Bevilacqua Michele","year":"2022","unstructured":"Michele Bevilacqua, Giuseppe Ottaviano, Patrick Lewis, Wen-tau Yih, Sebastian Riedel, and Fabio Petroni. 2022. Autoregressive Search Engines: Generating Substrings as Document Identifiers. arXiv preprint arXiv:2204.10628 (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Wizard of wikipedia: Knowledge-powered conversational agents. arXiv preprint arXiv:1811.01241","author":"Dinan Emily","year":"2018","unstructured":"Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. 2018. Wizard of wikipedia: Knowledge-powered conversational agents. arXiv preprint arXiv:1811.01241 (2018)."},{"key":"e_1_3_2_1_6_1","volume-title":"Wizard of Wikipedia: Knowledge-Powered Conversational Agents. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=r1l73iRqKm","author":"Dinan Emily","year":"2019","unstructured":"Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. 2019. Wizard of Wikipedia: Knowledge-Powered Conversational Agents. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=r1l73iRqKm"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC","author":"Elsahar Hady","year":"2018","unstructured":"Hady Elsahar, Pavlos Vougiouklis, Arslen Remaci, Christophe Gravier, Jonathon Hare, Frederique Laforest, and Elena Simperl. 2018. T-rex: A large scale alignment of natural language with knowledge base triples. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)."},{"key":"e_1_3_2_1_8_1","volume-title":"Md Faisal Mahbub Chowdhury, and Alfio Gliozzo","author":"Glass Michael","year":"2021","unstructured":"Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, and Alfio Gliozzo. 2021. Robust retrieval augmented generation for zero-shot slot filling. arXiv preprint arXiv:2108.13934 (2021)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.194"},{"key":"e_1_3_2_1_10_1","volume-title":"Ankita Rajaram Naik, Pengshan Cai, and Alfio Gliozzo.","author":"Glass Michael","year":"2022","unstructured":"Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Ankita Rajaram Naik, Pengshan Cai, and Alfio Gliozzo. 2022b. Re2G: Retrieve, Rerank, Generate. arXiv preprint arXiv:2207.06300 (2022)."},{"key":"e_1_3_2_1_11_1","volume-title":"Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling. In ICML 2022 Workshop on Knowledge Retrieval and Language Models.","author":"Sebastian","year":"2022","unstructured":"Sebastian Hofst\"atter, Jiecao Chen, Karthik Raman, and Hamed Zamani. 2022. Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling. In ICML 2022 Workshop on Knowledge Retrieval and Language Models."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591687"},{"key":"e_1_3_2_1_13_1","unstructured":"Gautier Izacard and Edouard Grave. 2020. Distilling Knowledge from Reader to Retriever for Question Answering. https:\/\/arxiv.org\/abs\/2012.04584"},{"key":"e_1_3_2_1_14_1","volume-title":"Categorical Reparameterization with Gumbel-Softmax. In International Conference on Learning Representations (ICLR '17)","author":"Jang Eric","year":"2017","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical Reparameterization with Gumbel-Softmax. In International Conference on Learning Representations (ICLR '17)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"e_1_3_2_1_16_1","volume-title":"Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oug uz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Machine Learning. PMLR, 3499--3508","author":"Kool Wouter","year":"2019","unstructured":"Wouter Kool, Herke Van Hoof, and Max Welling. 2019. Stochastic beams and where to find them: The gumbel-top-k trick for sampling sequences without replacement. In International Conference on Machine Learning. PMLR, 3499--3508."},{"key":"e_1_3_2_1_18_1","first-page":"47","article-title":"Ancestral Gumbel-Top-k Sampling for Sampling Without Replacement","volume":"21","author":"Kool Wouter","year":"2020","unstructured":"Wouter Kool, Herke van Hoof, and Max Welling. 2020. Ancestral Gumbel-Top-k Sampling for Sampling Without Replacement. J. Mach. Learn. Res. , Vol. 21 (2020), 47--1.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_20_1","volume-title":"Zero-shot relation extraction via reading comprehension. arXiv preprint arXiv:1706.04115","author":"Levy Omer","year":"2017","unstructured":"Omer Levy, Minjoon Seo, Eunsol Choi, and Luke Zettlemoyer. 2017. Zero-shot relation extraction via reading comprehension. arXiv preprint arXiv:1706.04115 (2017)."},{"key":"e_1_3_2_1_21_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\"aschel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems , Vol. 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","unstructured":"Huayang Li Yixuan Su Deng Cai Yan Wang and Lemao Liu. 2022. A Survey on Retrieval-Augmented Text Generation. arxiv: 2202.01110 [cs.CL]"},{"key":"e_1_3_2_1_23_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74--81. https:\/\/aclanthology.org\/W04--1013"},{"key":"e_1_3_2_1_24_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Maddison Chris J.","year":"2017","unstructured":"Chris J. Maddison, Andriy Mnih, and Yee Whye Teh. 2017. The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24--26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=S1jE5L5gl"},{"key":"e_1_3_2_1_25_1","unstructured":"Reiichiro Nakano Jacob Hilton Suchir Balaji Jeff Wu Long Ouyang Christina Kim Christopher Hesse Shantanu Jain Vineet Kosaraju William Saunders Xu Jiang Karl Cobbe Tyna Eloundou Gretchen Krueger Kevin Button Matthew Knight Benjamin Chess and John Schulman. 2022. WebGPT: Browser-assisted question-answering with human feedback. arxiv: 2112.09332 [cs.CL]"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_27_1","volume-title":"Hindsight: Posterior-guided training of retrievers for improved open-ended generation. arXiv preprint arXiv:2110.07752","author":"Paranjape Ashwin","year":"2021","unstructured":"Ashwin Paranjape, Omar Khattab, Christopher Potts, Matei Zaharia, and Christopher D Manning. 2021. Hindsight: Posterior-guided training of retrievers for improved open-ended generation. arXiv preprint arXiv:2110.07752 (2021)."},{"key":"e_1_3_2_1_28_1","volume-title":"Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator. In International Conference on Learning Representations (ICLR '21)","author":"Paulus Max B","year":"2021","unstructured":"Max B Paulus, Chris J. Maddison, and Andreas Krause. 2021. Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator. In International Conference on Learning Representations (ICLR '21)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.200"},{"key":"e_1_3_2_1_30_1","volume-title":"Edouard Grave, Wen-tau Yih, et al.","author":"Piktus Aleksandra","year":"2021","unstructured":"Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Dmytro Okhonko, Samuel Broscheit, Gautier Izacard, Patrick Lewis, Barlas Oug uz, Edouard Grave, Wen-tau Yih, et al. 2021. The Web Is Your Oyster--Knowledge-Intensive NLP against a Very Large Web Corpus. arXiv preprint arXiv:2112.09924 (2021)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463106"},{"key":"e_1_3_2_1_32_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research , Vol. 21 (2020), 1--67.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_33_1","unstructured":"Adam Roberts Hyung Won Chung Anselm Levskaya Gaurav Mishra James Bradbury Daniel Andor Sharan Narang Brian Lester Colin Gaffney Afroz Mohiuddin Curtis Hawthorne Aitor Lewkowycz Alex Salcianu Marc van Zee Jacob Austin Sebastian Goodman Livio Baldini Soares Haitang Hu Sasha Tsvyashchenko Aakanksha Chowdhery Jasmijn Bastings Jannis Bulian Xavier Garcia Jianmo Ni Andrew Chen Kathleen Kenealy Jonathan H. Clark Stephan Lee Dan Garrette James Lee-Thorp Colin Raffel Noam Shazeer Marvin Ritter Maarten Bosma Alexandre Passos Jeremy Maitin-Shepard Noah Fiedel Mark Omernick Brennan Saeta Ryan Sepassi Alexander Spiridonov Joshua Newlan and Andrea Gesmundo. 2022. Scaling Up Models and Data with $textttt5x$ and $textttseqio$. arXiv preprint arXiv:2203.17189 (2022)."},{"key":"e_1_3_2_1_34_1","volume-title":"Text Retrieval Conference. https:\/\/api.semanticscholar.org\/CorpusID:3946054","author":"Robertson Stephen E.","year":"1994","unstructured":"Stephen E. Robertson, Steve Walker, Susan Jones, Micheline Hancock-Beaulieu, and Mike Gatford. 1994. Okapi at TREC-3. In Text Retrieval Conference. https:\/\/api.semanticscholar.org\/CorpusID:3946054"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.519"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657783"},{"key":"e_1_3_2_1_37_1","volume-title":"LaMP: When Large Language Models Meet Personalization. arxiv: 2304","author":"Salemi Alireza","year":"2024","unstructured":"Alireza Salemi, Sheshera Mysore, Michael Bendersky, and Hamed Zamani. 2024 b. LaMP: When Large Language Models Meet Personalization. arxiv: 2304.11406 [cs.CL]"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657957"},{"key":"e_1_3_2_1_39_1","volume-title":"International Conference on Machine Learning. PMLR, 4596--4604","author":"Shazeer Noam","year":"2018","unstructured":"Noam Shazeer and Mitchell Stern. 2018. Adafactor: Adaptive learning rates with sublinear memory cost. In International Conference on Machine Learning. PMLR, 4596--4604."},{"key":"e_1_3_2_1_40_1","volume-title":"REPLUG: Retrieval-Augmented Black-Box Language Models. arxiv: 2301.12652 [cs.CL]","author":"Shi Weijia","year":"2023","unstructured":"Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Rich James, Mike Lewis, Luke Zettlemoyer, and Wen-tau Yih. 2023. REPLUG: Retrieval-Augmented Black-Box Language Models. arxiv: 2301.12652 [cs.CL]"},{"key":"e_1_3_2_1_41_1","unstructured":"EuiYul Song Sangryul Kim Haeju Lee Joonkee Kim and James Thorne. 2024. Re3val: Reinforced and Reranked Generative Retrieval. arxiv: 2401.16979 [cs.IR]"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/609"},{"key":"e_1_3_2_1_43_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS '14","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to Sequence Learning with Neural Networks. In Advances in Neural Information Processing Systems (NeurIPS '14, Vol. 27). Curran Associates, Inc."},{"key":"e_1_3_2_1_44_1","volume-title":"Fever: a large-scale dataset for fact extraction and verification. arXiv preprint arXiv:1803.05355","author":"Thorne James","year":"2018","unstructured":"James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018a. Fever: a large-scale dataset for fact extraction and verification. arXiv preprint arXiv:1803.05355 (2018)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1074"},{"key":"e_1_3_2_1_46_1","volume-title":"On the Planning Abilities of Large Language Models - A Critical Investigation. arXiv 2305.15771","author":"Valmeekam Karthik","year":"2023","unstructured":"Karthik Valmeekam, Matthew Marquez, Sarath Sreedharan, and Subbarao Kambhampati. 2023. On the Planning Abilities of Large Language Models - A Critical Investigation. arXiv 2305.15771 (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Tu Vu Mohit Iyyer Xuezhi Wang Noah Constant Jerry Wei Jason Wei Chris Tar Yun-Hsuan Sung Denny Zhou Quoc Le and Thang Luong. 2023. FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation. In arXiv.","DOI":"10.18653\/v1\/2024.findings-acl.813"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5713"},{"key":"e_1_3_2_1_49_1","volume-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In International Conference on Learning Representations (ICLR '21)","author":"Xiong Lee","year":"2021","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In International Conference on Learning Representations (ICLR '21)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18--1259"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539813.3545141"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531722"},{"key":"e_1_3_2_1_53_1","unstructured":"Fengbin Zhu Wenqiang Lei Chao Wang Jianming Zheng Soujanya Poria and Tat-Seng Chua. 2021. Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering. arxiv: 2101.00774 [cs.AI]"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657923","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:23:24Z","timestamp":1755840204000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657923"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":53,"alternative-id":["10.1145\/3626772.3657923","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657923","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}