{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:38:42Z","timestamp":1780443522122,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":162,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"General Research Funds from the Hong Kong Research Grants Council","award":["PolyU 15200021, 15207322, and 15200023"],"award-info":[{"award-number":["PolyU 15200021, 15207322, and 15200023"]}]},{"name":"internal research funds from The Hong Kong Polytechnic University","award":["P0036200, P0042693, P0048625, P0048752, and P0051361"],"award-info":[{"award-number":["P0036200, P0042693, P0048625, P0048752, and P0051361"]}]},{"name":"Research Collaborative Project","award":["P0041282"],"award-info":[{"award-number":["P0041282"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102335"],"award-info":[{"award-number":["62102335"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SHTM Interdisciplinary Large Grant","award":["P0043302"],"award-info":[{"award-number":["P0043302"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671470","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:54:55Z","timestamp":1724561695000},"page":"6491-6501","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":547,"title":["A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4049-1233","authenticated-orcid":false,"given":"Wenqi","family":"Fan","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2945-1107","authenticated-orcid":false,"given":"Yujuan","family":"Ding","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6903-8996","authenticated-orcid":false,"given":"Liangbo","family":"Ning","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7389-3810","authenticated-orcid":false,"given":"Shijie","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2369-1567","authenticated-orcid":false,"given":"Hengyun","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0684-6205","authenticated-orcid":false,"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, CN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National university of Singapore, Singapore, SG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Sweta Agrawal Chunting Zhou Mike Lewis Luke Zettlemoyer and Marjan Ghazvininejad. 2023. In-context Examples Selection for Machine Translation. In ACL (Findings). 8857--8873.","DOI":"10.18653\/v1\/2023.findings-acl.564"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Miles C Andrews Junna Oba Chang-Jiun Wu Haifeng Zhu Tatiana Karpinets Caitlin A Creasy Marie-Andr\u00e9e Forget Xiaoxing Yu Xingzhi Song Xizeng Mao et al. 2022. Multi-modal molecular programs regulate melanoma cell state. Nature communications Vol. 13 1 (2022) 4000.","DOI":"10.1038\/s41467-022-31510-1"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Akari Asai Sewon Min Zexuan Zhong and Danqi Chen. 2023. Retrieval-based language models and applications. In ACL (Tutorial). 41--46.","DOI":"10.18653\/v1\/2023.acl-tutorials.6"},{"key":"e_1_3_2_1_5_1","unstructured":"Akari Asai Zeqiu Wu Yizhong Wang Avirup Sil and Hannaneh Hajishirzi. 2023. Self-RAG: Learning to Retrieve Generate and Critique through Self-Reflection. In ICLR."},{"key":"e_1_3_2_1_6_1","volume-title":"Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, et al.","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 ICML. 2206--2240."},{"key":"e_1_3_2_1_7_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. In NeurIPS."},{"key":"e_1_3_2_1_8_1","volume-title":"Charles LA Clarke, and Gordon V Cormack","author":"Buttcher Stefan","year":"2016","unstructured":"Stefan Buttcher, Charles LA Clarke, and Gordon V Cormack. 2016. Information retrieval: Implementing and evaluating search engines. Mit Press."},{"key":"e_1_3_2_1_9_1","volume-title":"Accelerating large language model decoding with speculative sampling. arXiv:2302.01318","author":"Chen Charlie","year":"2023","unstructured":"Charlie Chen, Sebastian Borgeaud, Geoffrey Irving, Jean-Baptiste Lespiau, Laurent Sifre, and John Jumper. 2023. Accelerating large language model decoding with speculative sampling. arXiv:2302.01318 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Danqi Chen Adam Fisch Jason Weston and Antoine Bordes. 2017. Reading Wikipedia to Answer Open-Domain Questions. In ACL. 1870--1879.","DOI":"10.18653\/v1\/P17-1171"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Jingfan Chen Wenqi Fan Guanghui Zhu Xiangyu Zhao Chunfeng Yuan Qing Li and Yihua Huang. 2022. Knowledge-enhanced Black-box Attacks for Recommendations. In KDD. 108--117.","DOI":"10.1145\/3534678.3539359"},{"key":"e_1_3_2_1_12_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Xiao Chen Wenqi Fan Jingfan Chen Haochen Liu Zitao Liu Zhaoxiang Zhang and Qing Li. 2023. Fairly adaptive negative sampling for recommendations. In WWW. 3723--3733.","DOI":"10.1145\/3543507.3583355"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Xiuyi Chen Fandong Meng Peng Li Feilong Chen Shuang Xu Bo Xu and Jie Zhou. 2020. Bridging the gap between prior and posterior knowledge selection for knowledge-grounded dialogue generation. In EMNLP. 3426--3437.","DOI":"10.18653\/v1\/2020.emnlp-main.275"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Yudong Chen Zhihui Lai Yujuan Ding Kaiyi Lin and Wai Keung Wong. 2019. Deep supervised hashing with anchor graph. In ICCV. 9796--9804.","DOI":"10.1109\/ICCV.2019.00989"},{"key":"e_1_3_2_1_16_1","volume-title":"UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation. In EMNLP. 12318--12337.","author":"Cheng Daixuan","year":"2023","unstructured":"Daixuan Cheng, Shaohan Huang, Junyu Bi, Yuefeng Zhan, Jianfeng Liu, Yujing Wang, Hao Sun, Furu Wei, Weiwei Deng, and Qi Zhang. 2023. UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation. In EMNLP. 12318--12337."},{"key":"e_1_3_2_1_17_1","unstructured":"Xin Cheng Di Luo Xiuying Chen Lemao Liu Dongyan Zhao and Rui Yan. 2024. Lift yourself up: Retrieval-augmented text generation with self-memory. In NeurIPS."},{"key":"e_1_3_2_1_18_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language modeling with pathways. J Mach Learn Res, Vol. 24, 240 (2023), 1--113.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_2_1_19_1","volume-title":"Search engines: Information retrieval in practice","author":"Croft W Bruce","unstructured":"W Bruce Croft, Donald Metzler, and Trevor Strohman. 2010. Search engines: Information retrieval in practice. Vol. 520. Addison-Wesley Reading."},{"key":"e_1_3_2_1_20_1","volume-title":"Large legal fictions: Profiling legal hallucinations in large language models. arXiv:2401.01301","author":"Dahl Matthew","year":"2024","unstructured":"Matthew Dahl, Varun Magesh, Mirac Suzgun, and Daniel E Ho. 2024. Large legal fictions: Profiling legal hallucinations in large language models. arXiv:2401.01301 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"Cohen","author":"de Jong Michiel","year":"2022","unstructured":"Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald, Fei Sha, and William W. Cohen. 2022. Mention Memory: incorporating textual knowledge into Transformers through entity mention attention. In ICLR."},{"key":"e_1_3_2_1_22_1","volume-title":"Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning. arXiv:2402.08416","author":"Deng Gelei","year":"2024","unstructured":"Gelei Deng, Yi Liu, Kailong Wang, Yuekang Li, Tianwei Zhang, and Yang Liu. 2024. Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning. arXiv:2402.08416 (2024)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Ziqing Deng Zhihui Lai Yujuan Ding Heng Kong and Xu Wu. 2024. Deep Scaling Factor Quantization Network for Large-scale Image Retrieval. In ICMR. 851--859.","DOI":"10.1145\/3652583.3658017"},{"key":"e_1_3_2_1_24_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT (1). 4171--4186.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT (1). 4171--4186."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Dario Di Palma. 2023. Retrieval-augmented recommender system: Enhancing recommender systems with large language models. In RecSys. 1369--1373.","DOI":"10.1145\/3604915.3608889"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Yujuan Ding Yunshan Ma Wenqi Fan Yige Yao Tat-Seng Chua and Qing Li. 2024. FashionReGen: LLM-Empowered Fashion Report Generation. In WWW.","DOI":"10.1145\/3589335.3651232"},{"key":"e_1_3_2_1_27_1","first-page":"103434","article-title":"Personalized fashion outfit generation with user coordination preference learning","volume":"60","author":"Ding Yujuan","year":"2023","unstructured":"Yujuan Ding, P. Y. Mok, Yunshan Ma, and Yi Bin. 2023. Personalized fashion outfit generation with user coordination preference learning. IP&M, Vol. 60, 5 (2023), 103434.","journal-title":"IP&M"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2891246"},{"key":"e_1_3_2_1_29_1","first-page":"102288","article-title":"Discriminative dual-stream deep hashing for large-scale image retrieval","volume":"57","author":"Ding Yujuan","year":"2020","unstructured":"Yujuan Ding, Wai Keung Wong, Zhihui Lai, and Zheng Zhang. 2020. Discriminative dual-stream deep hashing for large-scale image retrieval. IP&M, Vol. 57, 6 (2020), 102288.","journal-title":"IP&M"},{"key":"e_1_3_2_1_30_1","unstructured":"Andrew Drozdov Nathanael Sch\u00e4rli Ekin Aky\u00fcrek Nathan Scales Xinying Song Xinyun Chen Olivier Bousquet and Denny Zhou. 2022. Compositional semantic parsing with large language models. In ICLR."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Wenqi Fan Tyler Derr Xiangyu Zhao Yao Ma Hui Liu Jianping Wang Jiliang Tang and Qing Li. 2021. Attacking black-box recommendations via copying cross-domain user profiles. In ICDE. 1583--1594.","DOI":"10.1109\/ICDE51399.2021.00140"},{"key":"e_1_3_2_1_32_1","volume-title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models. arXiv:2405.06211","author":"Fan Wenqi","year":"2024","unstructured":"Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024. A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models. arXiv:2405.06211 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Wenqi Fan Xiaorui Liu Wei Jin Xiangyu Zhao Jiliang Tang and Qing Li. 2022. Graph Trend Filtering Networks for Recommendation. In SIGIR. 112--121.","DOI":"10.1145\/3477495.3531985"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Wenqi Fan Yao Ma Qing Li Yuan He Eric Zhao Jiliang Tang and Dawei Yin. 2019. Graph neural networks for social recommendation. In WWW. 417--426.","DOI":"10.1145\/3308558.3313488"},{"key":"e_1_3_2_1_35_1","volume-title":"A graph neural network framework for social recommendations. TKDE","author":"Fan Wenqi","year":"2020","unstructured":"Wenqi Fan, Yao Ma, Qing Li, Jianping Wang, Guoyong Cai, Jiliang Tang, and Dawei Yin. 2020. A graph neural network framework for social recommendations. TKDE (2020)."},{"key":"e_1_3_2_1_36_1","unstructured":"Wenqi Fan Xiangyu Zhao Xiao Chen Jingran Su Jingtong Gao Lin Wang Qidong Liu Yiqi Wang Han Xu Lei Chen et al. 2022. A Comprehensive Survey on Trustworthy Recommender Systems. arXiv:2209.10117 (2022)."},{"key":"e_1_3_2_1_37_1","volume-title":"Recommender systems in the era of large language models (llms). arXiv:2307.02046","author":"Fan Wenqi","year":"2023","unstructured":"Wenqi Fan, Zihuai Zhao, Jiatong Li, Yunqing Liu, Xiaowei Mei, Yiqi Wang, Jiliang Tang, and Qing Li. 2023. Recommender systems in the era of large language models (llms). arXiv:2307.02046 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Nicholas FitzGerald, Eunsol Choi, and Tom Kwiatkowski.","author":"F\u00e9vry Thibault","year":"2020","unstructured":"Thibault F\u00e9vry, Livio Baldini Soares, Nicholas FitzGerald, Eunsol Choi, and Tom Kwiatkowski. 2020. Entities as Experts: Sparse Memory Access with Entity Supervision. In EMNLP. 4937--4951."},{"key":"e_1_3_2_1_39_1","volume-title":"Retrieval-augmented generation for large language models: A survey. arXiv:2312.10997","author":"Gao Yunfan","year":"2023","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 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Unsupervised dense information retrieval with contrastive learning. J Mach Learn Res","author":"Gautier Izacard","year":"2022","unstructured":"Izacard Gautier, Caron Mathilde, Hosseini Lucas, Riedel Sebastian, Bojanowski Piotr, Joulin Armand, and Grave Edouard. 2022. Unsupervised dense information retrieval with contrastive learning. J Mach Learn Res (2022)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11977"},{"key":"e_1_3_2_1_42_1","volume-title":"Ankita Naik, Pengshan Cai, and Alfio Gliozzo.","author":"Glass Michael R.","year":"2022","unstructured":"Michael R. Glass, Gaetano Rossiello, Md. Faisal Mahbub Chowdhury, Ankita Naik, Pengshan Cai, and Alfio Gliozzo. 2022. Re2G: Retrieve, Rerank, Generate. In NAACL-HLT. 2701--2715."},{"key":"e_1_3_2_1_43_1","unstructured":"Edouard Grave Armand Joulin and Nicolas Usunier. 2017. Improving Neural Language Models with a Continuous Cache. In ICLR."},{"key":"e_1_3_2_1_44_1","unstructured":"Kelvin Guu Kenton Lee Zora Tung Panupong Pasupat and Mingwei Chang. 2020. Retrieval augmented language model pre-training. In ICML. 3929--3938."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Junxian He Graham Neubig and Taylor Berg-Kirkpatrick. 2021. Efficient Nearest Neighbor Language Models. In EMNLP (1). 5703--5714.","DOI":"10.18653\/v1\/2021.emnlp-main.461"},{"key":"e_1_3_2_1_46_1","volume-title":"Rest: Retrieval-based speculative decoding. arXiv:2311.08252","author":"He Zhenyu","year":"2023","unstructured":"Zhenyu He, Zexuan Zhong, Tianle Cai, Jason D Lee, and Di He. 2023. Rest: Retrieval-based speculative decoding. arXiv:2311.08252 (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"Reveal: Retrieval-augmented visual-language pre-training with multi-source multimodal knowledge memory. In CVPR. 23369--23379.","author":"Hu Ziniu","year":"2023","unstructured":"Ziniu Hu, Ahmet Iscen, Chen Sun, Zirui Wang, Kai-Wei Chang, Yizhou Sun, Cordelia Schmid, David A Ross, and Alireza Fathi. 2023. Reveal: Retrieval-augmented visual-language pre-training with multi-source multimodal knowledge memory. In CVPR. 23369--23379."},{"key":"e_1_3_2_1_48_1","volume-title":"Kevin Chen-Chuan Chang, and Bryan Catanzaro","author":"Huang Jie","year":"2023","unstructured":"Jie Huang, Wei Ping, Peng Xu, Mohammad Shoeybi, Kevin Chen-Chuan Chang, and Bryan Catanzaro. 2023. Raven: In-context learning with retrieval augmented encoder-decoder language models. arXiv:2308.07922 (2023)."},{"key":"e_1_3_2_1_49_1","unstructured":"Gautier Izacard and Edouard Grave. 2021. Distilling Knowledge from Reader to Retriever for Question Answering. In ICLR."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Gautier Izacard and Edouard Grave. 2021. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. In EACL. 874--880.","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"e_1_3_2_1_51_1","first-page":"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, 251 (2023), 1--43.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Zhengbao Jiang Frank F Xu Luyu Gao Zhiqing Sun Qian Liu Jane Dwivedi-Yu Yiming Yang Jamie Callan and Graham Neubig. 2023. Active Retrieval Augmented Generation. In EMNLP. 7969--7992.","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"e_1_3_2_1_53_1","volume-title":"Genta Winata, Samuel Cahyawijaya, Anuoluwapo Aremu, Perez Ogayo, and Graham Neubig.","author":"Kabra Anubha","year":"2023","unstructured":"Anubha Kabra, Emmy Liu, Simran Khanuja, Alham Fikri Aji, Genta Winata, Samuel Cahyawijaya, Anuoluwapo Aremu, Perez Ogayo, and Graham Neubig. 2023. Multi-lingual and Multi-cultural Figurative Language Understanding. In ACL."},{"key":"e_1_3_2_1_54_1","volume-title":"Jinheon Baek, and Sung Ju Hwang.","author":"Kang Minki","year":"2023","unstructured":"Minki Kang, Jin Myung Kwak, Jinheon Baek, and Sung Ju Hwang. 2023. Knowledge graph-augmented language models for knowledge-grounded dialogue generation. arXiv:2305.18846 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Vladimir Karpukhin Barlas Oguz Sewon Min Patrick S. H. Lewis Ledell Wu Sergey Edunov Danqi Chen and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In EMNLP. 6769--6781.","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_56_1","unstructured":"Urvashi Khandelwal Omer Levy Dan Jurafsky Luke Zettlemoyer and Mike Lewis. 2020. Generalization through Memorization: Nearest Neighbor Language Models. In ICLR."},{"key":"e_1_3_2_1_57_1","volume-title":"David Hall, Percy Liang, Christopher Potts, and Matei Zaharia.","author":"Khattab Omar","year":"2022","unstructured":"Omar Khattab, Keshav Santhanam, Xiang Lisa Li, David Hall, Percy Liang, Christopher Potts, and Matei Zaharia. 2022. Demonstrate-search-predict: Composing retrieval and language models for knowledge-intensive nlp. arXiv:2212.14024 (2022)."},{"key":"e_1_3_2_1_58_1","volume-title":"Colbert: Efficient and effective passage search via contextualized late interaction over bert. In SIGIR. 39--48.","author":"Khattab Omar","year":"2020","unstructured":"Omar Khattab and Matei Zaharia. 2020. Colbert: Efficient and effective passage search via contextualized late interaction over bert. In SIGIR. 39--48."},{"key":"e_1_3_2_1_59_1","unstructured":"Gangwoo Kim Sungdong Kim Byeongguk Jeon Joonsuk Park and Jaewoo Kang. 2023. Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models. In EMNLP."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/358923.358934"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"crossref","unstructured":"Mojtaba Komeili Kurt Shuster and Jason Weston. 2022. Internet-Augmented Dialogue Generation. In ACL. 8460--8478.","DOI":"10.18653\/v1\/2022.acl-long.579"},{"key":"e_1_3_2_1_62_1","unstructured":"Tian Lan Deng Cai Yan Wang Heyan Huang and Xian-Ling Mao. 2022. Copy is All You Need. In ICLR."},{"key":"e_1_3_2_1_63_1","unstructured":"Yaniv Leviathan Matan Kalman and Yossi Matias. 2023. Fast inference from transformers via speculative decoding. In ICML. 19274--19286."},{"key":"e_1_3_2_1_64_1","unstructured":"Mike Lewis Marjan Ghazvininejad Gargi Ghosh Armen Aghajanyan Sida Wang and Luke Zettlemoyer. 2020. Pre-training via paraphrasing. In NeurIPS."},{"key":"e_1_3_2_1_65_1","volume-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL. 7871--7880.","author":"Lewis Mike","year":"2020","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL. 7871--7880."},{"key":"e_1_3_2_1_66_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. In NeurIPS. 9459--9474."},{"key":"e_1_3_2_1_67_1","unstructured":"Hongxin Li Jingran Su Yuntao Chen Qing Li and ZHAO-XIANG ZHANG. 2024. SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models. In NeurIPS."},{"key":"e_1_3_2_1_68_1","volume-title":"Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective. arXiv:2306.06615","author":"Li Jiatong","year":"2023","unstructured":"Jiatong Li, Yunqing Liu, Wenqi Fan, Xiao-Yong Wei, Hui Liu, Jiliang Tang, and Qing Li. 2023. Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective. arXiv:2306.06615 (2023)."},{"key":"e_1_3_2_1_69_1","volume-title":"AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework. arXiv:2403.12582","author":"Li Xiang","year":"2024","unstructured":"Xiang Li, Zhenyu Li, Chen Shi, Yong Xu, Qing Du, Mingkui Tan, Jun Huang, and Wei Lin. 2024. AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework. arXiv:2403.12582 (2024)."},{"key":"e_1_3_2_1_70_1","unstructured":"Xinze Li Zhenghao Liu Chenyan Xiong Shi Yu Yu Gu Zhiyuan Liu and Ge Yu. 2023. Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data. In ACL."},{"key":"e_1_3_2_1_71_1","volume-title":"NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following.","author":"Li Xiaoqian","year":"2023","unstructured":"Xiaoqian Li, Ercong Nie, and Sheng Liang. 2023. From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"crossref","unstructured":"Xiaonan Li and Xipeng Qiu. 2023. MoT: Memory-of-Thought Enables ChatGPT to Self-Improve. In EMNLP. 6354--6374.","DOI":"10.18653\/v1\/2023.emnlp-main.392"},{"key":"e_1_3_2_1_73_1","unstructured":"Zonglin Li Ruiqi Guo and Sanjiv Kumar. 2022. Decoupled context processing for context augmented language modeling. In NeurIPS. 21698--21710."},{"key":"e_1_3_2_1_74_1","volume-title":"Revolutionizing Retrieval-Augmented Generation with Enhanced PDF Structure Recognition. arXiv:2401.12599","author":"Lin Demiao","year":"2024","unstructured":"Demiao Lin. 2024. Revolutionizing Retrieval-Augmented Generation with Enhanced PDF Structure Recognition. arXiv:2401.12599 (2024)."},{"key":"e_1_3_2_1_75_1","unstructured":"Xi Victoria Lin Xilun Chen Mingda Chen Weijia Shi Maria Lomeli Richard James Pedro Rodriguez Jacob Kahn Gergely Szilvasy Mike Lewis et al. 2023. RA-DIT: Retrieval-Augmented Dual Instruction Tuning. In ICLR."},{"key":"e_1_3_2_1_76_1","unstructured":"Haochen Liu Jamell Dacon Wenqi Fan Hui Liu Zitao Liu and Jiliang Tang. 2020. Does Gender Matter? Towards Fairness in Dialogue Systems. In ACL."},{"key":"e_1_3_2_1_77_1","volume-title":"Trustworthy ai: A computational perspective. arXiv:2107.06641","author":"Liu Haochen","year":"2021","unstructured":"Haochen Liu, Yiqi Wang, Wenqi Fan, Xiaorui Liu, Yaxin Li, Shaili Jain, Yunhao Liu, Anil K Jain, and Jiliang Tang. 2021. Trustworthy ai: A computational perspective. arXiv:2107.06641 (2021)."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00759-6"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"crossref","unstructured":"Ye Liu Semih Yavuz Rui Meng Dragomir Radev Caiming Xiong and Yingbo Zhou. 2022. Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database. In EMNLP. 8858--8869.","DOI":"10.18653\/v1\/2022.emnlp-main.605"},{"key":"e_1_3_2_1_80_1","volume-title":"PACIFIC SYMPOSIUM ON BIOCOMPUTING","author":"Lozano Alejandro","year":"2023","unstructured":"Alejandro Lozano, Scott L Fleming, Chia-Chun Chiang, and Nigam Shah. 2023. Clinfo. ai: An open-source retrieval-augmented large language model system for answering medical questions using scientific literature. In PACIFIC SYMPOSIUM ON BIOCOMPUTING 2024. 8--23."},{"key":"e_1_3_2_1_81_1","volume-title":"Song-Chun Zhu, Tanmay Rajpurohit, Peter Clark, and Ashwin Kalyan.","author":"Lu Pan","year":"2023","unstructured":"Pan Lu, Liang Qiu, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, Tanmay Rajpurohit, Peter Clark, and Ashwin Kalyan. 2023. Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning. In ICLR."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"crossref","unstructured":"Yu Lu Junwei Bao Yan Song Zichen Ma Shuguang Cui Youzheng Wu and Xiaodong He. 2021. RevCore: Review-Augmented Conversational Recommendation. In ACL\/IJCNLP (Findings). 1161--1173.","DOI":"10.18653\/v1\/2021.findings-acl.99"},{"key":"e_1_3_2_1_83_1","volume-title":"icl: Demonstration-retrieved in-context learning. arXiv:2305.14128","author":"Luo Man","year":"2023","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 (2023)."},{"key":"e_1_3_2_1_84_1","volume-title":"Retrieved Sequence Augmentation for Protein Representation Learning. bioRxiv","author":"Ma Chang","year":"2023","unstructured":"Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, and Lingpeng Kong. 2023. Retrieved Sequence Augmentation for Protein Representation Learning. bioRxiv (2023), 2023--02."},{"key":"e_1_3_2_1_85_1","volume-title":"Query rewriting for retrieval-augmented large language models. arXiv:2305.14283","author":"Ma Xinbei","year":"2023","unstructured":"Xinbei Ma, Yeyun Gong, Pengcheng He, Hai Zhao, and Nan Duan. 2023. Query rewriting for retrieval-augmented large language models. arXiv:2305.14283 (2023)."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.genbench-1.14"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"crossref","unstructured":"Sewon Min Julian Michael Hannaneh Hajishirzi and Luke Zettlemoyer. 2020. AmbigQA: Answering Ambiguous Open-domain Questions. In EMNLP.","DOI":"10.18653\/v1\/2020.emnlp-main.466"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"crossref","unstructured":"Sewon Min Weijia Shi Mike Lewis Xilun Chen Wen-tau Yih Hannaneh Hajishirzi and Luke Zettlemoyer. 2023. Nonparametric Masked Language Modeling. In ACL (Findings). 2097--2118.","DOI":"10.18653\/v1\/2023.findings-acl.132"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"crossref","unstructured":"Noor Nashid Mifta Sintaha and Ali Mesbah. 2023. Retrieval-based prompt selection for code-related few-shot learning. In ICSE. 2450--2462.","DOI":"10.1109\/ICSE48619.2023.00205"},{"key":"e_1_3_2_1_90_1","volume-title":"Rossano Schifanella, Yunlong He, Dawei Yin, and Yi Chang.","author":"O'Hare Neil","year":"2016","unstructured":"Neil O'Hare, Paloma De Juan, Rossano Schifanella, Yunlong He, Dawei Yin, and Yi Chang. 2016. Leveraging user interaction signals for web image search. In SIGIR. 559--568."},{"key":"e_1_3_2_1_91_1","volume-title":"Saikat Chakraborty, Baishakhi Ray, and Kai-Wei Chang.","author":"Rizwan Parvez Md.","year":"2021","unstructured":"Md. Rizwan Parvez, Wasi Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray, and Kai-Wei Chang. 2021. Retrieval Augmented Code Generation and Summarization. In EMNLP (Findings). 2719--2734."},{"key":"e_1_3_2_1_92_1","unstructured":"Fabio Petroni Patrick S. H. Lewis Aleksandra Piktus Tim Rockt\u00e4schel Yuxiang Wu Alexander H. Miller and Sebastian Riedel. 2020. How Context Affects Language Models' Factual Predictions. In AKBC."},{"key":"e_1_3_2_1_93_1","volume-title":"Synchromesh: Reliable Code Generation from Pre-trained Language Models. In ICLR.","author":"Poesia Gabriel","year":"2022","unstructured":"Gabriel Poesia, Alex Polozov, Vu Le, Ashish Tiwari, Gustavo Soares, Christopher Meek, and Sumit Gulwani. 2022. Synchromesh: Reliable Code Generation from Pre-trained Language Models. In ICLR."},{"key":"e_1_3_2_1_94_1","volume-title":"Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interface. arXiv:2310.04205","author":"Purwar Anupam","year":"2023","unstructured":"Anupam Purwar and Rahul Sundar. 2023. Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interface. arXiv:2310.04205 (2023)."},{"key":"e_1_3_2_1_95_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In ICML. 8748--8763."},{"key":"e_1_3_2_1_96_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_97_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. J Mach Learn Res, Vol. 21, 140 (2020), 1--67.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00605"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"crossref","unstructured":"Ori Ram Gal Shachaf Omer Levy Jonathan Berant and Amir Globerson. 2022. Learning to Retrieve Passages without Supervision. In NAACL-HLT. 2687--2700.","DOI":"10.18653\/v1\/2022.naacl-main.193"},{"key":"e_1_3_2_1_100_1","unstructured":"Parikshit Ram and Alexander G Gray. 2012. Maximum inner-product search using cone trees. In KDD. 931--939."},{"key":"e_1_3_2_1_101_1","volume-title":"Proceedings of the first instructional conference on machine learning","volume":"242","author":"Juan","unstructured":"Juan Ramos et al. 2003. Using tf-idf to determine word relevance in document queries. In Proceedings of the first instructional conference on machine learning, Vol. 242. Citeseer, 29--48."},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"crossref","unstructured":"Rita Ramos Bruno Martins Desmond Elliott and Yova Kementchedjhieva. 2023. Smallcap: lightweight image captioning prompted with retrieval augmentation. In CVPR. 2840--2849.","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"e_1_3_2_1_103_1","volume-title":"Reichman and Larry Heck","author":"Benjamin","year":"2024","unstructured":"Benjamin Z. Reichman and Larry Heck. 2024. Retrieval-Augmented Generation: Is Dense Passage Retrieval Retrieving? https:\/\/arxiv.org\/html\/2402.11035v1 (2024)."},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"crossref","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In EMNLP-IJCNLP. 3982--3992.","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_105_1","volume-title":"Retrieve-and-sample: Document-level event argument extraction via hybrid retrieval augmentation. In ACL. 293--306.","author":"Ren Yubing","year":"2023","unstructured":"Yubing Ren, Yanan Cao, Ping Guo, Fang Fang, Wei Ma, and Zheng Lin. 2023. Retrieve-and-sample: Document-level event argument extraction via hybrid retrieval augmentation. In ACL. 293--306."},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_107_1","doi-asserted-by":"crossref","unstructured":"Ohad Rubin Jonathan Herzig and Jonathan Berant. 2022. Learning To Retrieve Prompts for In-Context Learning. In NAACL-HLT. 2655--2671.","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"crossref","unstructured":"Sara Sarto Marcella Cornia Lorenzo Baraldi and Rita Cucchiara. 2022. Retrieval-augmented transformer for image captioning. In CBMI. 1--7.","DOI":"10.1145\/3549555.3549585"},{"key":"e_1_3_2_1_109_1","volume-title":"Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom.","author":"Schick Timo","year":"2024","unstructured":"Timo Schick, Jane Dwivedi-Yu, Roberto Dess`i, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2024. Toolformer: Language models can teach themselves to use tools. In NeurIPS."},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"crossref","unstructured":"Zhihong Shao Yeyun Gong Minlie Huang Nan Duan Weizhu Chen et al. 2023. Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy. In EMNLP.","DOI":"10.18653\/v1\/2023.findings-emnlp.620"},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"crossref","unstructured":"Fumin Shen Wei Liu Shaoting Zhang Yang Yang and Heng Tao Shen. 2015. Learning binary codes for maximum inner product search. In ICCV. 4148--4156.","DOI":"10.1109\/ICCV.2015.472"},{"key":"e_1_3_2_1_112_1","unstructured":"Shelly Sheynin Oron Ashual Adam Polyak Uriel Singer Oran Gafni Eliya Nachmani and Yaniv Taigman. 2023. kNN-Diffusion: Image Generation via Large-Scale Retrieval. In ICLR."},{"key":"e_1_3_2_1_113_1","volume-title":"XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing. In EMNLP (Findings). 5248--5259.","author":"Shi Peng","year":"2022","unstructured":"Peng Shi, Rui Zhang, He Bai, and Jimmy Lin. 2022. XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing. In EMNLP (Findings). 5248--5259."},{"key":"e_1_3_2_1_114_1","volume-title":"Replug: Retrieval-augmented black-box language models. arXiv:2301.12652","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 (2023)."},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"crossref","unstructured":"Guy Shtar. 2021. Multimodal machine learning for drug knowledge discovery. In WSDM. 1115--1116.","DOI":"10.1145\/3437963.3441671"},{"key":"e_1_3_2_1_116_1","doi-asserted-by":"crossref","unstructured":"Kurt Shuster Spencer Poff Moya Chen Douwe Kiela and Jason Weston. 2021. Retrieval Augmentation Reduces Hallucination in Conversation. In EMNLP (Findings). 3784--3803.","DOI":"10.18653\/v1\/2021.findings-emnlp.320"},{"key":"e_1_3_2_1_117_1","volume-title":"In-context learning as maintaining coherency: A study of on-the-fly machine translation using large language models. arXiv:2305.03573","author":"Sia Suzanna","year":"2023","unstructured":"Suzanna Sia and Kevin Duh. 2023. In-context learning as maintaining coherency: A study of on-the-fly machine translation using large language models. arXiv:2305.03573 (2023)."},{"key":"e_1_3_2_1_118_1","first-page":"35","article-title":"Modern information retrieval: A brief overview","volume":"24","author":"Amit Singhal","year":"2001","unstructured":"Amit Singhal et al. 2001. Modern information retrieval: A brief overview. IEEE Data Eng. Bull., Vol. 24, 4 (2001), 35--43.","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_3_2_1_119_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00530"},{"key":"e_1_3_2_1_120_1","volume-title":"Hisum: Hyperbolic interaction model for extractive multi-document summarization. In WWW. 1427--1436.","author":"Song Mingyang","year":"2023","unstructured":"Mingyang Song, Yi Feng, and Liping Jing. 2023. Hisum: Hyperbolic interaction model for extractive multi-document summarization. In WWW. 1427--1436."},{"key":"e_1_3_2_1_121_1","doi-asserted-by":"publisher","DOI":"10.1108\/eb026526"},{"key":"e_1_3_2_1_122_1","volume-title":"Jae Hun Ro, Ahmad Beirami, Himanshu Jain, and Felix Yu.","author":"Sun Ziteng","year":"2024","unstructured":"Ziteng Sun, Ananda Theertha Suresh, Jae Hun Ro, Ahmad Beirami, Himanshu Jain, and Felix Yu. 2024. Spectr: Fast speculative decoding via optimal transport. In NeurIPS."},{"key":"e_1_3_2_1_123_1","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 (2023)."},{"key":"e_1_3_2_1_124_1","doi-asserted-by":"crossref","unstructured":"Harsh Trivedi Niranjan Balasubramanian Tushar Khot and Ashish Sabharwal. 2023. Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions. In ACL.","DOI":"10.18653\/v1\/2023.acl-long.557"},{"key":"e_1_3_2_1_125_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103874"},{"key":"e_1_3_2_1_126_1","doi-asserted-by":"crossref","unstructured":"Boxin Wang Wei Ping Peng Xu Lawrence McAfee Zihan Liu Mohammad Shoeybi Yi Dong Oleksii Kuchaiev Bo Li Chaowei Xiao et al. 2023. Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study. In EMNLP. 7763--7786.","DOI":"10.18653\/v1\/2023.emnlp-main.482"},{"key":"e_1_3_2_1_127_1","volume-title":"Rethinking Large Language Model Architectures for Sequential Recommendations. arXiv:2402.09543","author":"Wang Hanbing","year":"2024","unstructured":"Hanbing Wang, Xiaorui Liu, Wenqi Fan, Xiangyu Zhao, Venkataramana Kini, Devendra Yadav, Fei Wang, Zhen Wen, Jiliang Tang, and Hui Liu. 2024. Rethinking Large Language Model Architectures for Sequential Recommendations. arXiv:2402.09543 (2024)."},{"key":"e_1_3_2_1_128_1","unstructured":"Liang Wang Nan Yang and Furu Wei. 2024. Learning to Retrieve In-Context Examples for Large Language Models. In EACL. 1752--1767."},{"key":"e_1_3_2_1_129_1","volume-title":"2023 f. Knowledgpt: Enhancing large language models with retrieval and storage access on knowledge bases. arXiv:2308.11761","author":"Wang Xintao","year":"2023","unstructured":"Xintao Wang, Qianwen Yang, Yongting Qiu, Jiaqing Liang, Qianyu He, Zhouhong Gu, Yanghua Xiao, and Wei Wang. 2023 f. Knowledgpt: Enhancing large language models with retrieval and storage access on knowledge bases. arXiv:2308.11761 (2023)."},{"key":"e_1_3_2_1_130_1","doi-asserted-by":"crossref","unstructured":"Yile Wang Peng Li Maosong Sun and Yang Liu. 2023. Self-Knowledge Guided Retrieval Augmentation for Large Language Models. In EMNLP.","DOI":"10.18653\/v1\/2023.findings-emnlp.691"},{"key":"e_1_3_2_1_131_1","unstructured":"Zichao Wang Weili Nie Zhuoran Qiao Chaowei Xiao Richard G. Baraniuk and Anima Anandkumar. 2023. Retrieval-based Controllable Molecule Generation. In ICLR."},{"key":"e_1_3_2_1_132_1","volume-title":"2023 e. BioBridge: Bridging Biomedical Foundation Models via Knowledge Graph. arXiv:2310.03320","author":"Wang Zifeng","year":"2023","unstructured":"Zifeng Wang, Zichen Wang, Balasubramaniam Srinivasan, Vassilis N Ioannidis, Huzefa Rangwala, and Rishita Anubhai. 2023 e. BioBridge: Bridging Biomedical Foundation Models via Knowledge Graph. arXiv:2310.03320 (2023)."},{"key":"e_1_3_2_1_133_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. In NeurIPS. 24824--24837."},{"key":"e_1_3_2_1_134_1","volume-title":"CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation. arXiv:2403.06447","author":"Wu Junda","year":"2024","unstructured":"Junda Wu, Cheng-Chun Chang, Tong Yu, Zhankui He, Jianing Wang, Yupeng Hou, and Julian McAuley. 2024. CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation. arXiv:2403.06447 (2024)."},{"key":"e_1_3_2_1_135_1","unstructured":"Ledell Wu Fabio Petroni Martin Josifoski Sebastian Riedel and Luke Zettlemoyer. 2020. Scalable Zero-shot Entity Linking with Dense Entity Retrieval. In EMNLP. 6397--6407."},{"key":"e_1_3_2_1_136_1","volume-title":"DeLesley Hutchins, and Christian Szegedy.","author":"Wu Yuhuai","year":"2022","unstructured":"Yuhuai Wu, Markus Norman Rabe, DeLesley Hutchins, and Christian Szegedy. 2022. Memorizing Transformers. In ICLR."},{"key":"e_1_3_2_1_137_1","volume-title":"RECOMP: Improving retrieval-augmented LMs with context compression and selective augmentation. In ICLR.","author":"Xu Fangyuan","year":"2023","unstructured":"Fangyuan Xu, Weijia Shi, and Eunsol Choi. 2023. RECOMP: Improving retrieval-augmented LMs with context compression and selective augmentation. In ICLR."},{"key":"e_1_3_2_1_138_1","unstructured":"Jitao Xu Josep-Maria Crego and Jean Senellart. 2020. Boosting neural machine translation with similar translations. In ACL. 1570--1579."},{"key":"e_1_3_2_1_139_1","unstructured":"Jing Xu Arthur Szlam and Jason Weston. 2022. Beyond Goldfish Memory: Long-Term Open-Domain Conversation. In ACL (1). 5180--5197."},{"key":"e_1_3_2_1_140_1","unstructured":"Ling Yang Zhilin Huang Xiangxin Zhou Minkai Xu Wentao Zhang Yu Wang Xiawu Zheng Wenming Yang Ron O Dror Shenda Hong et al. 2023. Prompt-based 3d molecular diffusion models for structure-based drug design. (2023)."},{"key":"e_1_3_2_1_141_1","unstructured":"Jiacheng Ye Zhiyong Wu Jiangtao Feng Tao Yu and Lingpeng Kong. 2023. Compositional exemplars for in-context learning. In ICML. 39818--39833."},{"key":"e_1_3_2_1_142_1","doi-asserted-by":"crossref","unstructured":"Yunhu Ye Binyuan Hui Min Yang Binhua Li Fei Huang and Yongbin Li. 2023. Large Language Models are Versatile Decomposers: Decomposing Evidence and Questions for Table-based Reasoning. In SIGIR. 174--184.","DOI":"10.1145\/3539618.3591708"},{"key":"e_1_3_2_1_143_1","volume-title":"Financial Report Chunking for Effective Retrieval Augmented Generation. arXiv:2402.05131","author":"Yepes Antonio Jimeno","year":"2024","unstructured":"Antonio Jimeno Yepes, Yao You, Jan Milczek, Sebastian Laverde, and Leah Li. 2024. Financial Report Chunking for Effective Retrieval Augmented Generation. arXiv:2402.05131 (2024)."},{"key":"e_1_3_2_1_144_1","doi-asserted-by":"crossref","unstructured":"Dawei Yin Yuening Hu Jiliang Tang Tim Daly Mianwei Zhou Hua Ouyang Jianhui Chen Changsung Kang Hongbo Deng Chikashi Nobata et al. 2016. Ranking relevance in yahoo search. In KDD. 323--332.","DOI":"10.1145\/2939672.2939677"},{"key":"e_1_3_2_1_145_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00371"},{"key":"e_1_3_2_1_146_1","unstructured":"Ori Yoran Tomer Wolfson Ori Ram and Jonathan Berant. 2023. Making Retrieval-Augmented Language Models Robust to Irrelevant Context. In ICLR."},{"key":"e_1_3_2_1_147_1","unstructured":"Wenhao Yu Dan Iter Shuohang Wang Yichong Xu Mingxuan Ju Soumya Sanyal Chenguang Zhu Michael Zeng and Meng Jiang. 2023. Generate rather than Retrieve: Large Language Models are Strong Context Generators. In ICLR."},{"key":"e_1_3_2_1_148_1","volume-title":"Improving language models via plug-and-play retrieval feedback. arXiv:2305.14002","author":"Yu Wenhao","year":"2023","unstructured":"Wenhao Yu, Zhihan Zhang, Zhenwen Liang, Meng Jiang, and Ashish Sabharwal. 2023. Improving language models via plug-and-play retrieval feedback. arXiv:2305.14002 (2023)."},{"key":"e_1_3_2_1_149_1","doi-asserted-by":"crossref","unstructured":"Zichun Yu Chenyan Xiong Shi Yu and Zhiyuan Liu. 2023. Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In. In ACL. 2421--2436.","DOI":"10.18653\/v1\/2023.acl-long.136"},{"key":"e_1_3_2_1_150_1","doi-asserted-by":"crossref","unstructured":"Shenglai Zeng Jiankun Zhang Pengfei He Yue Xing Yiding Liu Han Xu Jie Ren Shuaiqiang Wang Dawei Yin Yi Chang et al. 2024. The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG). arXiv:2402.16893 (2024).","DOI":"10.18653\/v1\/2024.findings-acl.267"},{"key":"e_1_3_2_1_151_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626866"},{"key":"e_1_3_2_1_152_1","doi-asserted-by":"crossref","unstructured":"Houyu Zhang Zhenghao Liu Chenyan Xiong and Zhiyuan Liu. 2020. Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs. In ACL. 2031--2043.","DOI":"10.18653\/v1\/2020.acl-main.184"},{"key":"e_1_3_2_1_153_1","volume-title":"Linear-Time Graph Neural Networks for Scalable Recommendations. arXiv:2402.13973","author":"Zhang Jiahao","year":"2024","unstructured":"Jiahao Zhang, Rui Xue, Wenqi Fan, Xin Xu, Qing Li, Jian Pei, and Xiaorui Liu. 2024. Linear-Time Graph Neural Networks for Scalable Recommendations. arXiv:2402.13973 (2024)."},{"key":"e_1_3_2_1_154_1","volume-title":"Merging generated and retrieved knowledge for open-domain QA. arXiv:2310.14393","author":"Zhang Yunxiang","year":"2023","unstructured":"Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, and Lu Wang. 2023. Merging generated and retrieved knowledge for open-domain QA. arXiv:2310.14393 (2023)."},{"key":"e_1_3_2_1_155_1","volume-title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey. arXiv:2402.19473","author":"Zhao Penghao","year":"2024","unstructured":"Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, and Bin Cui. 2024. Retrieval-Augmented Generation for AI-Generated Content: A Survey. arXiv:2402.19473 (2024)."},{"key":"e_1_3_2_1_156_1","volume-title":"Chengwei Qin, Bosheng Ding, Xiaobao Guo, Minzhi Li, Xingxuan Li, et al.","author":"Zhao Ruochen","year":"2023","unstructured":"Ruochen Zhao, Hailin Chen, Weishi Wang, Fangkai Jiao, Xuan Long Do, Chengwei Qin, Bosheng Ding, Xiaobao Guo, Minzhi Li, Xingxuan Li, et al. 2023. Retrieving multimodal information for augmented generation: A survey. arXiv:2303.10868 (2023)."},{"key":"e_1_3_2_1_157_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_158_1","doi-asserted-by":"crossref","unstructured":"Zihuai Zhao Wenqi Fan Jiatong Li Yunqing Liu Xiaowei Mei Yiqi Wang Zhen Wen Fei Wang Xiangyu Zhao Jiliang Tang et al. 2024. Recommender systems in the era of large language models (llms). TKDE (2024).","DOI":"10.1109\/TKDE.2024.3392335"},{"key":"e_1_3_2_1_159_1","doi-asserted-by":"crossref","unstructured":"Zexuan Zhong Tao Lei and Danqi Chen. 2022. Training Language Models with Memory Augmentation. In EMNLP.","DOI":"10.18653\/v1\/2022.emnlp-main.382"},{"key":"e_1_3_2_1_160_1","volume-title":"Docprompting: Generating code by retrieving the docs. In ICLR.","author":"Zhou Shuyan","year":"2022","unstructured":"Shuyan Zhou, Uri Alon, Frank F Xu, Zhengbao Jiang, and Graham Neubig. 2022. Docprompting: Generating code by retrieving the docs. In ICLR."},{"key":"e_1_3_2_1_161_1","volume-title":"REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models. arXiv:2402.07016","author":"Zhu Yinghao","year":"2024","unstructured":"Yinghao Zhu, Changyu Ren, Shiyun Xie, Shukai Liu, Hangyuan Ji, Zixiang Wang, Tao Sun, Long He, Zhoujun Li, Xi Zhu, et al. 2024. REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models. arXiv:2402.07016 (2024)."},{"key":"e_1_3_2_1_162_1","volume-title":"PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models. arXiv:2402.07867","author":"Zou Wei","year":"2024","unstructured":"Wei Zou, Runpeng Geng, Binghui Wang, and Jinyuan Jia. 2024. PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models. arXiv:2402.07867 (2024)."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671470","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:18Z","timestamp":1750291458000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671470"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":162,"alternative-id":["10.1145\/3637528.3671470","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671470","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}