The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization
Abstract
This paper introduces Stochastic RAG--a novel approach for end-to-end optimization of retrieval-augmented generation (RAG) models that relaxes the simplifying assumptions of marginalization and document independence, made in most prior work. Stochastic RAG casts the retrieval process in RAG as a stochastic sampling without replacement process. Through this formulation, we employ straight-through Gumbel-top-k that provides a differentiable approximation for sampling without replacement and enables effective end-to-end optimization for RAG. We conduct extensive experiments on seven diverse datasets on a wide range of tasks, from open-domain question answering to fact verification to slot-filling for relation extraction and to dialogue systems. By applying this optimization method to a recent and effective RAG model, we advance state-of-the-art results on six out of seven datasets.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Stochastic RAG [200] employs stochastic sampling without replacement to address the non-differentiable topk selection process in RAG retrieval, enabling end-to-end optimization and achieving excellent results in fact verification scenarios.”
From Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024) · cites this paper as [200]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Dense passage retrieval for open-domain question answering
Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-T. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.550 · Cited by 3,575
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.11401 · Cited by 3,101
Natural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069
TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Joshi, M., Choi, E., Weld, D., & Zettlemoyer, L. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1147 · Cited by 1,690
TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Joshi, M., Choi, E., Weld, D. S., & Zettlemoyer, L. (2017) · arXiv · doi:10.48550/arxiv.1705.03551 · Cited by 1,650
FEVER: a Large-scale Dataset for Fact Extraction and VERification
Thorne, J., Vlachos, A., Christodoulopoulos, C., & Mittal, A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1074 · Cited by 1,343 · cited 1×
“We use the Natural Questions (NQ) [19], TriviaQA [15], HotpotQA [50], FEVER [45], T-REx [7], zsRE [20], and Wizard of Wikipedia (WoW) [6] datasets from the KILT [29] benchmark.”
MethodZero-Shot Relation Extraction via Reading Comprehension
Levy, O., Seo, M., Choi, E., & Zettlemoyer, L. (2017) · Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017) · doi:10.18653/v1/k17-1034 · Cited by 482 · cited 1×
“We use the Natural Questions (NQ) [19], TriviaQA [15], HotpotQA [50], FEVER [45], T-REx [7], zsRE [20], and Wizard of Wikipedia (WoW) [6] datasets from the KILT [29] benchmark.”
MethodRetrieve and Refine: Improved Sequence Generation Models For Dialogue
Weston, J., Dinan, E., & Miller, A. (2018) · Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI · doi:10.18653/v1/w18-5713 · Cited by 165
Distilling Knowledge from Reader to Retriever for Question Answering
Izacard, G., & Grave, E. (2020) · arXiv · doi:10.48550/arxiv.2012.04584 · Cited by 102 · cited 1×
“There exist solutions based on knowledge distillation [13] or end-to-end optimization based on some simplifying assumptions [35].”
BackgroundAutoregressive Search Engines: Generating Substrings as Document Identifiers
Bevilacqua, M., Ottaviano, G., Lewis, P., Yih, W.-T., Riedel, S., & Petroni, F. (2022) · arXiv · doi:10.48550/arxiv.2204.10628 · Cited by 80
FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation
Vu, T., Iyyer, M., Wang, X., Constant, N., Wei, J., Wei, J., Tar, C., Sung, Y.-H., Zhou, D., Le, Q., et al. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.813 · Cited by 73
Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation
Salemi, A., Kallumadi, S., & Zamani, H. (2024) · Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3626772.3657783 · Cited by 52 · cited 1×
“RAG models demonstrate substantial promise across various applications, including open-domain question answering [16, 21, 53], fact verification [44], dialogue systems [5, 42, 48], and personalized generation [36, 37].”
BackgroundSelf-citationFiD-Light: Efficient and Effective Retrieval-Augmented Text Generation
Hofstätter, S., Chen, J., Raman, K., & Zamani, H. (2022) · arXiv · doi:10.48550/arxiv.2209.14290 · Cited by 51
Self-citation
Research works printed but not linked: 41
- 10.1145/3583780.3614901 · DOI
- 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). · arXiv
- 10.18653/v1/2022.findings-aacl.10 · DOI
- 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). · arXiv
- 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
- 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).
- 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). · arXiv
- 10.18653/v1/2022.naacl-main.194 · DOI · Paper page
- 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). · arXiv
- 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.
- 10.1145/3539618.3591687 · DOI · Paper page
- Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical Reparameterization with Gumbel-Softmax. In International Conference on Learning Representations (ICLR '17).
- 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.
- 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.
- Huayang Li Yixuan Su Deng Cai Yan Wang and Lemao Liu. 2022. A Survey on Retrieval-Augmented Text Generation. arxiv: 2202.01110 [cs.CL] · arXiv
- 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
- 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
- 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] · arXiv
- 10.3115/1073083.1073135 · DOI · Paper page
- 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). · arXiv
- 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).
- 10.18653/v1/2021.naacl-main.200 · DOI · Paper page
- 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). · arXiv
- 10.1145/3404835.3463106 · DOI
- 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). · arXiv
- 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
- 10.18653/v1/2021.acl-long.519 · DOI
- Alireza Salemi, Sheshera Mysore, Michael Bendersky, and Hamed Zamani. 2024 b. LaMP: When Large Language Models Meet Personalization. arxiv: 2304.11406 [cs.CL] · arXiv
- 10.1145/3626772.3657957 · DOI
- Noam Shazeer and Mitchell Stern. 2018. Adafactor: Adaptive learning rates with sublinear memory cost. In International Conference on Machine Learning. PMLR, 4596--4604.
- 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] · arXiv
- EuiYul Song Sangryul Kim Haeju Lee Joonkee Kim and James Thorne. 2024. Re3val: Reinforced and Reranked Generative Retrieval. arxiv: 2401.16979 [cs.IR] · arXiv
- 10.24963/ijcai.2018/609 · DOI
- 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.
- 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). · arXiv
- 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). · arXiv
- 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).
- 10.18653/v1/D18--1259 · doi:10.18653/v1/d18--1259
- 10.1145/3539813.3545141 · DOI
- 10.1145/3477495.3531722 · DOI
- 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] · arXiv
Cited by
Retrieval-Augmented Generation for AI-Generated Content: A Survey
Zhao, P., Zhang, H., Yu, Q., Wang, Z., Geng, Y., Fu, F., Yang, L., Zhang, W., Jiang, J., & Cui, B. (2024) · arXiv · doi:10.48550/arxiv.2402.19473 · Cited by 240
“Counterfactual Robustness refers to the ability of LLMs to identify counterfactual errors in the retrieved content.”
Accelerating Retrieval-Augmented Generation
Quinn, D., Nouri, M., Patel, N., Salihu, J., Salemi, A., Lee, S., Zamani, H., & Alian, M. (2025) · Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1 · doi:10.1145/3669940.3707264 · Cited by 48
Self-citationIpa, A. S., Rony, M. A. T., & Islam, M. S. (2025) · Proceedings of the 1st Workshop on Language Models for Underserved Communities (LM4UC 2025) · doi:10.18653/v1/2025.lm4uc-1.2 · Cited by 3
“Stochastic RAG (Zamani and Bendersky, 2024) introduces an end-to-end optimization framework that utilizes straight-through Gumbel-top-k selection, enhancing retrieval and generation efficiency while achieving state-of-the-art re-sults across multiple tasks.”
Metadata
- Authors
- Zamani, H., & Bendersky, M.
- Affiliations
- University of Massachusetts Amherst, Amherst, MA, USA
- Google, Mountain View, CA, USA
- Venue
- Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval
- Publisher
- ACM
- Published
- 2024-07-10
- Pages
- 2641-2646
- Cited by
- 31
- References
- 14
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.