Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization-Reference-Cited by-同舟云学术

Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization

Published:2024-07-10 Issue: Volume:21 Page:2641-2646
ISSN:
Container-title:Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval
language:
Short-container-title:

Author:

Zamani Hamed¹^ORCID,Bendersky Michael²^ORCID

Affiliation:

1. University of Massachusetts Amherst, Amherst, MA, USA

2. Google, Mountain View, CA, USA

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3626772.3657923

Reference53 articles.

1. GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking

2. 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).

3. Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhihua Wu, Zhen Guo, Hua Lu, Xinxian Huang, Xin Tian, Xinchao Xu, Yingzhan Lin, and Zheng-Yu Niu. 2022. PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation. In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022, , Yulan He, Heng Ji, Sujian Li, Yang Liu, and Chua-Hui Chang (Eds.). Association for Computational Linguistics, Online only, 107--118. https://aclanthology.org/2022.findings-aacl.10

4. 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).

5. 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).

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Evaluating Retrieval Quality in Retrieval-Augmented Generation;Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval;2024-07-10

2. Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Models;Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval;2024-07-10