{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:16:43Z","timestamp":1778948203822,"version":"3.51.4"},"reference-count":76,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"name":"National Key Research and Development Program of China","award":["2024YFE0203200"],"award-info":[{"award-number":["2024YFE0203200"]}]},{"DOI":"10.13039\/501100003246","name":"Dutch Research Council","doi-asserted-by":"crossref","award":["024.004.022, NWA.1389.20.183, and KICH3.LTP.20.006"],"award-info":[{"award-number":["024.004.022, NWA.1389.20.183, and KICH3.LTP.20.006"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"crossref"}]},{"name":"European Union\u2019s Horizon Europe program","award":["agreement No. 101070212 (FINDHR) and No. 101201510 (UNITE)"],"award-info":[{"award-number":["agreement No. 101070212 (FINDHR) and No. 101201510 (UNITE)"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>\n                    <jats:bold>Retrieval-augmented Generation (RAG)<\/jats:bold>\n                    integrates\n                    <jats:bold>Large Language Models (LLMs)<\/jats:bold>\n                    with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG performance, most previous work independently fine-tunes the retriever to adapt to frozen LLMs or trains the LLMs to use documents retrieved by off-the-shelf retrievers, lacking end-to-end training supervision. Recent work addresses this limitation by jointly training these two components but relies on overly simplifying assumptions of document independence, which has been criticized for being far from real-world scenarios. Thus, effectively optimizing the overall RAG performance remains a critical challenge.\n                  <\/jats:p>\n                  <jats:p>\n                    We propose a\n                    <jats:bold>\n                      Direct Retrieval-augmented Optimization (\n                      <jats:sc>DRO<\/jats:sc>\n                      )\n                    <\/jats:bold>\n                    framework that enables end-to-end training of two key components: (i) a generative knowledge selection model and (ii) an LLM generator.\n                    <jats:sc>DRO<\/jats:sc>\n                    alternates between two phases: (i) document permutation estimation and (ii) re-weighted maximization, progressively improving RAG components through a variational approach. In the estimation step, we treat\n                    <jats:italic toggle=\"yes\">document permutation<\/jats:italic>\n                    as a latent variable and directly estimate its distribution from the selection model by applying an importance sampling strategy. In the maximization step, we calibrate the optimization expectation using importance weights and jointly train the selection model and LLM generator. Our theoretical analysis reveals that\n                    <jats:sc>DRO<\/jats:sc>\n                    is analogous to policy-gradient methods in reinforcement learning. Extensive experiments conducted on five datasets illustrate that\n                    <jats:sc>DRO<\/jats:sc>\n                    outperforms the best baseline with 5\u201315% improvements in EM and F1. We also qualitatively analyze the stability, convergence, and variance of DRO. (Code is available on\n                    <jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"tois-2025-0333-uf01.jpg\"\/>\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/mangopy\/direct-rag-learning\">DRO GitHub<\/jats:ext-link>\n                    ).\n                  <\/jats:p>","DOI":"10.1145\/3795527","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T14:06:50Z","timestamp":1771855610000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9658-4906","authenticated-orcid":false,"given":"Zhengliang","family":"Shi","sequence":"first","affiliation":[{"name":"Leiden University, Leiden, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6547-1984","authenticated-orcid":false,"given":"Lingyong","family":"Yan","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4817-9500","authenticated-orcid":false,"given":"Weiwei","family":"Sun","sequence":"additional","affiliation":[{"name":"LTI, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6665-6406","authenticated-orcid":false,"given":"Yue","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Birmingham, Birmingham, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2964-6422","authenticated-orcid":false,"given":"Pengjie","family":"Ren","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5511-9370","authenticated-orcid":false,"given":"Xinyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9212-1947","authenticated-orcid":false,"given":"Shuaiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0684-6205","authenticated-orcid":false,"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-0202","authenticated-orcid":false,"given":"Maarten","family":"de Rijke","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9076-6565","authenticated-orcid":false,"given":"Zhaochun","family":"Ren","sequence":"additional","affiliation":[{"name":"Leiden University, Leiden, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,11]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.662"},{"key":"e_1_3_1_3_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations (ICLR \u201924)","author":"Asai Akari","year":"2024","unstructured":"Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-RAG: Learning to retrieve, generate, and critique through self-reflection. In Proceedings of the 12th International Conference on Learning Representations (ICLR \u201924). OpenReview.net."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0017089500002135"},{"key":"e_1_3_1_5_2","unstructured":"Shehzaad Dhuliawala Mojtaba Komeili Jing Xu Roberta Raileanu Xian Li Asli Celikyilmaz and Jason Weston. 2023. Chain-of-verification reduces hallucination in large language models. arXiv:2309.11495. Retrieved from https:\/\/arxiv.org\/abs\/2309.11495"},{"key":"e_1_3_1_6_2","unstructured":"Emily Dinan Stephen Roller Kurt Shuster Angela Fan Michael Auli and Jason Weston. 2018. Wizard of Wikipedia: Knowledge-powered conversational agents. arXiv:1811.01241. Retrieved from https:\/\/arxiv.org\/abs\/1811.01241"},{"key":"e_1_3_1_7_2","unstructured":"Guanting Dong Yutao Zhu Chenghao Zhang Zechen Wang Zhicheng Dou and Ji-Rong Wen. 2024. Understand what LLM needs: Dual preference alignment for retrieval-augmented generation. arXiv:2406.18676. Retrieved from https:\/\/arxiv.org\/abs\/2406.18676"},{"key":"e_1_3_1_8_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The Llama 3 Herd of models. arXiv:2407.21783. Retrieved from https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_1_9_2","doi-asserted-by":"crossref","unstructured":"V\u00edctor Elvira and Luca Martino. 2021. Advances in importance sampling. arXiv:2102.05407. Retrieved from https:\/\/arxiv.org\/abs\/2102.05407","DOI":"10.1002\/9781118445112.stat08284"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671470"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.540"},{"key":"e_1_3_1_12_2","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yi Dai Jiawei Sun and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv:2312.10997. Retrieved from https:\/\/arxiv.org\/abs\/2312.10997"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102067"},{"key":"e_1_3_1_14_2","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. Retrieval augmented language model pre-training. In Proceedings of the International Conference on Machine Learning. PMLR."},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.580"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591687"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_3_1_18_2","first-page":"11912","article-title":"Atlas: Few-shot learning with retrieval augmented language models","volume":"251","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. Journal of Machine Learning Research 251 (2023), 11912\u201311954.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_1_19_2","unstructured":"Albert Qiaochu Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra Singh Chaplot Diego de Las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier et al. 2023. Mistral 7B. arXiv:2310.06825. Retrieved from https:\/\/arxiv.org\/abs\/2310.06825"},{"key":"e_1_3_1_20_2","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra Singh Chaplot Diego de las Casas Emma Bou Hanna Florian Bressand et al. 2024. Mixtral of experts. arXiv:2401.04088. Retrieved from https:\/\/arxiv.org\/abs\/2401.04088"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.2307\/1913641"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3496517"},{"key":"e_1_3_1_25_2","volume-title":"Proceedings of the 2024 ACM SIGIR International Conference on Theory of Information Retrieval","author":"Li Xiaoxi","year":"2024","unstructured":"Xiaoxi Li, Zhicheng Dou, Yujia Zhou, and Fangchao Liu. 2024. CorpusLM: Towards a unified language model on corpus for knowledge-intensive tasks. In Proceedings of the 2024 ACM SIGIR International Conference on Theory of Information Retrieval."},{"key":"e_1_3_1_26_2","unstructured":"Xinze Li Sen Mei Zhenghao Liu Yukun Yan Shuo Wang Shi Yu Zheni Zeng Hao Chen Ge Yu Zhiyuan Liu et al. 2024. RAG-DDR: Optimizing retrieval-augmented generation using differentiable data rewards. arXiv:2410.13509. Retrieved from https:\/\/arxiv.org\/abs\/2410.13509"},{"key":"e_1_3_1_27_2","unstructured":"Jiachen Lian Xuanru Zhou Zoe Ezzes Jet Vonk Brittany Morin David Baquirin Zachary Mille Maria Luisa Gorno Tempini and Gopala Krishna Anumanchipalli. 2024. SSDM: Scalable speech dysfluency modeling. arXiv:2408.16221. Retrieved from https:\/\/arxiv.org\/abs\/2408.16221"},{"key":"e_1_3_1_28_2","unstructured":"Xi Victoria Lin Xilun Chen Mingda Chen Weijia Shi Maria Lomeli Rich James Pedro Rodriguez Jacob Kahn Gergely Szilvasy Mike Lewis et al. 2023. RA-DIT: Retrieval-augmented dual instruction tuning. arXiv:2310.01352. Retrieved from https:\/\/arxiv.org\/abs\/2310.01352"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_1_30_2","unstructured":"Zihan Liu Wei Ping Rajarshi Roy Peng Xu Chankyu Lee Mohammad Shoeybi and Bryan Catanzaro. 2024. ChatQA: Surpassing GPT-4 on conversational QA and RAG. arXiv:2401.10225. Retrieved from https:\/\/arxiv.org\/abs\/2401.10225"},{"key":"e_1_3_1_31_2","unstructured":"Xueguang Ma Xinyu Zhang Ronak Pradeep and Jimmy Lin. 2023. Zero-shot listwise document reranking with a large language model. arXiv:2305.02156. Retrieved from https:\/\/arxiv.org\/abs\/2305.02156"},{"key":"e_1_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Sewon Min Kenton Lee Ming-Wei Chang Kristina Toutanova and Hannaneh Hajishirzi. 2021. Joint passage ranking for diverse multi-answer retrieval. arXiv:2104.08445. Retrieved from https:\/\/arxiv.org\/abs\/2104.08445","DOI":"10.18653\/v1\/2021.emnlp-main.560"},{"key":"e_1_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Sewon Min Julian Michael Hannaneh Hajishirzi and Luke Zettlemoyer. 2020. AmbigQA: Answering ambiguous open-domain questions. arXiv:2004.10645. Retrieved from https:\/\/arxiv.org\/abs\/2004.10645","DOI":"10.18653\/v1\/2020.emnlp-main.466"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/79.543975"},{"key":"e_1_3_1_35_2","volume-title":"Proceedings of the Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches 2016 co-Located with the 30th Annual Conference on Neural Information Processing Systems (NIPS \u201916)","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A human generated machine reading comprehension dataset. In Proceedings of the Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches 2016 co-Located with the 30th Annual Conference on Neural Information Processing Systems (NIPS \u201916). Retrieved from https:\/\/ceur-ws.org\/Vol-1773\/CoCoNIPS_2016_paper9.pdf"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.200"},{"key":"e_1_3_1_38_2","unstructured":"Ronak Pradeep Sahel Sharifymoghaddam and Jimmy Lin. 2023. RankVicuna: Zero-shot listwise document reranking with open-source large language models. arXiv:2309.15088. Retrieved from https:\/\/arxiv.org\/abs\/2309.15088"},{"key":"e_1_3_1_39_2","unstructured":"Ronak Pradeep Sahel Sharifymoghaddam and Jimmy Lin. 2023. RankZephyr: Effective and robust zero-shot listwise reranking is a breeze! arXiv:2312.02724. Retrieved from https:\/\/arxiv.org\/abs\/2312.02724"},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Rafael Rafailov Archit Sharma Eric Mitchell Christopher D. Manning Stefano Ermon and Chelsea Finn. 2024. Direct preference optimization: Your language model is secretly a reward model. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS \u201923) 53728\u201353741.","DOI":"10.52202\/075280-2338"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00605"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1540"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.519"},{"key":"e_1_3_1_45_2","unstructured":"Devendra Singh Sachan Mike Lewis Mandar Joshi Armen Aghajanyan Wen-Tau Yih Joelle Pineau and Luke Zettlemoyer. 2022. Improving passage retrieval with zero-shot question generation. arXiv:2204.07496. Retrieved from https:\/\/arxiv.org\/abs\/2204.07496"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657957"},{"key":"e_1_3_1_47_2","first-page":"3715","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Santhanam Keshav","year":"2021","unstructured":"Keshav Santhanam, O. Khattab, Jon Saad-Falcon, Christopher Potts, and Matei A. Zaharia. 2021. ColBERTv2: Effective and efficient retrieval via lightweight late interaction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 3715\u20133734."},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.620"},{"key":"e_1_3_1_49_2","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. Retrieved from https:\/\/arxiv.org\/abs\/2301.12652"},{"key":"e_1_3_1_50_2","unstructured":"Zhengliang Shi Weiwei Sun Shen Gao Pengjie Ren Zhumin Chen and Zhaochun Ren. 2024. Generate-then-ground in retrieval-augmented generation for multi-hop question answering. arXiv:2406.14891. Retrieved from https:\/\/arxiv.org\/abs\/2406.14891"},{"key":"e_1_3_1_51_2","unstructured":"Zhengliang Shi Weiwei Sun Shuo Zhang Zhen Zhang Pengjie Ren and Zhaochun Ren. 2023. RADE: Reference-assisted dialogue evaluation for open-domain dialogue. arXiv:2309.08156. Retrieved from https:\/\/arxiv.org\/abs\/2309.08156"},{"key":"e_1_3_1_52_2","first-page":"25968","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS \u201921)","author":"Singh Devendra","year":"2021","unstructured":"Devendra Singh, Siva Reddy, Will Hamilton, Chris Dyer, and Dani Yogatama. 2021. End-to-end training of multi-document reader and retriever for open-domain question answering. In Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS \u201921), 25968\u201325981."},{"key":"e_1_3_1_53_2","first-page":"58128","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS \u201923)","author":"Sordoni Alessandro","year":"2024","unstructured":"Alessandro Sordoni, Eric Yuan, Marc-Alexandre C\u00f4t\u00e9, Matheus Pereira, Adam Trischler, Ziang Xiao, Arian Hosseini, Friederike Niedtner, and Nicolas Le Roux. 2024. Joint prompt optimization of stacked LLMs using variational inference. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS \u201923), 58128\u201358151."},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3673791.3698403"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.155"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"e_1_3_1_57_2","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Sun Zhiqing","year":"2020","unstructured":"Zhiqing Sun and Yiming Yang. 2020. An EM approach to non-autoregressive conditional sequence generation. In Proceedings of the International Conference on Machine Learning. PMLR."},{"key":"e_1_3_1_58_2","first-page":"1057","volume-title":"Proceedings of the Proceedings of the 13th International Conference on Neural Information Processing Systems (NIPS \u201999)","author":"Sutton Richard S.","year":"1999","unstructured":"Richard S. Sutton, David McAllester, Satinder Singh, and Yishay Mansour. 1999. Policy gradient methods for reinforcement learning with function approximation. In Proceedings of the Proceedings of the 13th International Conference on Neural Information Processing Systems (NIPS \u201999), 1057\u20131063."},{"key":"e_1_3_1_59_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv:2307.09288. Retrieved from https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00475"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_1_62_2","unstructured":"Shuting Wang Jiongnan Liu Shiren Song Jiehan Cheng Yuqi Fu Peidong Guo Kun Fang Yutao Zhu and Zhicheng Dou. 2024. DomainRAG: A Chinese benchmark for evaluating domain-specific retrieval-augmented generation. arXiv:2406.05654. Retrieved from https:\/\/arxiv.org\/abs\/2406.05654"},{"key":"e_1_3_1_63_2","unstructured":"Shuting Wang Xin Yu Mang Wang Weipeng Chen Yutao Zhu and Zhicheng Dou. 2024. RichRAG: Crafting rich responses for multi-faceted queries in retrieval-augmented generation. arXiv:2406.12566. Retrieved from https:\/\/arxiv.org\/abs\/2406.12566"},{"key":"e_1_3_1_64_2","unstructured":"Zhiruo Wang Jun Araki Zhengbao Jiang Md Rizwan Parvez and Graham Neubig. 2023. Learning to filter context for retrieval-augmented generation. arXiv:2311.08377. Retrieved from https:\/\/arxiv.org\/abs\/2311.08377"},{"key":"e_1_3_1_65_2","unstructured":"Zhepei Wei Wei-Lin Chen and Yu Meng. 2024. InstructRAG: Instructing retrieval-augmented generation via self-synthesized rationales. arXiv:2406.13629. Retrieved from https:\/\/arxiv.org\/abs\/2406.13629"},{"key":"e_1_3_1_66_2","unstructured":"Shitao Xiao Zheng Liu Peitian Zhang and Niklas Muennighoff. 2023. C-Pack: Packaged resources to advance general Chinese embedding. arXiv:2309.07597. Retrieved from https:\/\/arxiv.org\/abs\/2309.07597"},{"key":"e_1_3_1_67_2","unstructured":"Fangyuan Xu Weijia Shi and Eunsol Choi. 2023. RECOMP: Improving retrieval-augmented LMs with compression and selective augmentation. arXiv:2310.04408. Retrieved from https:\/\/arxiv.org\/abs\/2310.04408"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645363"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657760"},{"key":"e_1_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"e_1_3_1_71_2","unstructured":"Ori Yoran Tomer Wolfson Ori Ram and Jonathan Berant. 2023. Making retrieval-augmented language models robust to irrelevant context. arXiv:2310.01558. Retrieved from https:\/\/arxiv.org\/abs\/2310.01558"},{"key":"e_1_3_1_72_2","unstructured":"Yue Yu Wei Ping Zihan Liu Boxin Wang Jiaxuan You Chao Zhang Mohammad Shoeybi and Bryan Catanzaro. 2024. RankRAG: Unifying context ranking with retrieval-augmented generation in LLMs. arXiv:2407.02485. Retrieved from https:\/\/arxiv.org\/abs\/2407.02485"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657923"},{"key":"e_1_3_1_74_2","unstructured":"Yue Zhang Yafu Li Leyang Cui Deng Cai Lemao Liu Tingchen Fu Xinting Huang Enbo Zhao Yu Zhang Yulong Chen et al. 2023. Siren\u2019s song in the AI ocean: A survey on hallucination in large language models. arXiv:2309.01219. Retrieved from https:\/\/arxiv.org\/abs\/2309.01219"},{"key":"e_1_3_1_75_2","first-page":"13637","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS \u201923)","author":"Zhao Hanyang","year":"2024","unstructured":"Hanyang Zhao, Wenpin Tang, and David Yao. 2024. Policy optimization for continuous reinforcement learning. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS \u201923), 13637\u201313663."},{"key":"e_1_3_1_76_2","unstructured":"Jianan Zhao Meng Qu Chaozhuo Li Hao Yan Qian Liu Rui Li Xing Xie and Jian Tang. 2022. Learning on large-scale text-attributed graphs via variational inference. arXiv:2210.14709. Retrieved from https:\/\/arxiv.org\/abs\/2210.14709"},{"key":"e_1_3_1_77_2","doi-asserted-by":"crossref","unstructured":"Junda Zhu Lingyong Yan Haibo Shi Dawei Yin and Lei Sha. 2024. ATM: Adversarial tuning multi-agent system makes a robust retrieval-augmented generator. arXiv:2405.18111. Retrieved from https:\/\/arxiv.org\/abs\/2405.18111","DOI":"10.18653\/v1\/2024.emnlp-main.610"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3795527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T15:45:14Z","timestamp":1778946314000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3795527"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,11]]},"references-count":76,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3795527"],"URL":"https:\/\/doi.org\/10.1145\/3795527","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,11]]},"assertion":[{"value":"2025-05-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}