{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:16:43Z","timestamp":1784179003971,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657878","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"641-649","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":323,"title":["C-Pack: Packed Resources For General Chinese Embeddings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2567-6843","authenticated-orcid":false,"given":"Shitao","family":"Xiao","sequence":"first","affiliation":[{"name":"Beijing Academy of AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7765-8466","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Academy of AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1926-7433","authenticated-orcid":false,"given":"Peitian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7157-770X","authenticated-orcid":false,"given":"Niklas","family":"Muennighoff","sequence":"additional","affiliation":[{"name":"HuggingFace, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3507-9607","authenticated-orcid":false,"given":"Defu","family":"Lian","sequence":"additional","affiliation":[{"name":"UTSC, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1556-3335","authenticated-orcid":false,"given":"Jian-Yun","family":"Nie","sequence":"additional","affiliation":[{"name":"University of Montreal, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/2387636.2387697"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Eneko Agirre Carmen Banea Claire Cardie Daniel M Cer Mona T Diab Aitor Gonzalez-Agirre Weiwei Guo Rada Mihalcea German Rigau and Janyce Wiebe. 2014. SemEval-2014 Task 10: Multilingual Semantic Textual Similarity.. In SemEval@ COLING. 81--91.","DOI":"10.3115\/v1\/S14-2010"},{"key":"e_1_3_2_1_3_1","first-page":"497","volume-title":"10th International Workshop on Semantic Evaluation; 2016 Jun 16-17; San Diego, CA","author":"Agirre Eneko","year":"2016","unstructured":"Eneko Agirre, Carmen Banea, Daniel Cer, Mona Diab, Aitor Gonzalez Agirre, Rada Mihalcea, German Rigau Claramunt, and Janyce Wiebe. 2016. Semeval-2016 task 1: Semantic textual similarity, monolingual and cross-lingual evaluation. In SemEval-2016. 10th International Workshop on Semantic Evaluation; 2016 Jun 16-17; San Diego, CA. Stroudsburg (PA): ACL; 2016. p. 497--511. ACL (Association for Computational Linguistics)."},{"key":"e_1_3_2_1_4_1","unstructured":"Eneko Agirre Daniel Cer Mona Diab and Aitor Gonzalez-Agirre. 2012. Semeval-2012 task 6: A pilot on semantic textual similarity. In * SEM 2012: The First Joint Conference on Lexical and Computational Semantics-Volume 1: Proceedings of the main conference and the shared task and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012). 385--393."},{"key":"e_1_3_2_1_5_1","volume-title":"Second joint conference on lexical and computational semantics (* SEM)","author":"Agirre Eneko","unstructured":"Eneko Agirre, Daniel Cer, Mona Diab, Aitor Gonzalez-Agirre, and Weiwei Guo. 2013. * SEM 2013 shared task: Semantic textual similarity. In Second joint conference on lexical and computational semantics (* SEM), volume 1: proceedings of the Main conference and the shared task: semantic textual similarity. 32--43."},{"key":"e_1_3_2_1_6_1","volume-title":"Niklas Muennighoff, Mayank Mishra, Alex Gu, Manan Dey, et al.","author":"Allal Loubna Ben","year":"2023","unstructured":"Loubna Ben Allal, Raymond Li, Denis Kocetkov, Chenghao Mou, Christopher Akiki, Carlos Munoz Ferrandis, Niklas Muennighoff, Mayank Mishra, Alex Gu, Manan Dey, et al. 2023. SantaCoder: don't reach for the stars! arXiv preprint arXiv:2301.03988 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Task-aware retrieval with instructions. arXiv preprint arXiv:2211.09260","author":"Asai Akari","year":"2022","unstructured":"Akari Asai, Timo Schick, Patrick Lewis, Xilun Chen, Gautier Izacard, Sebastian Riedel, Hannaneh Hajishirzi, and Wen-tau Yih. 2022. Task-aware retrieval with instructions. arXiv preprint arXiv:2211.09260 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"Israel Campiotti, Marzieh Fadaee, Roberto Lotufo, and Rodrigo Nogueira.","author":"Bonifacio Luiz","year":"2021","unstructured":"Luiz Bonifacio, Vitor Jeronymo, Hugo Queiroz Abonizio, Israel Campiotti, Marzieh Fadaee, Roberto Lotufo, and Rodrigo Nogueira. 2021. mmarco: A multilingual version of the ms marco passage ranking dataset. arXiv preprint arXiv:2108.13897 (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"International conference on machine learning. PMLR, 2206--2240","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 International conference on machine learning. PMLR, 2206--2240."},{"key":"e_1_3_2_1_10_1","volume-title":"A large annotated corpus for learning natural language inference. arXiv preprint arXiv:1508.05326","author":"Bowman Samuel R","year":"2015","unstructured":"Samuel R Bowman, Gabor Angeli, Christopher Potts, and Christopher D Manning. 2015. A large annotated corpus for learning natural language inference. arXiv preprint arXiv:1508.05326 (2015)."},{"key":"e_1_3_2_1_11_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. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_12_1","volume-title":"Charles Sutton, Sebastian Gehrmann, et al.","author":"Chowdhery Aakanksha","year":"2022","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2022. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)."},{"key":"e_1_3_2_1_13_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Eric Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma et al. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"SentEval: An Evaluation Toolkit for Universal Sentence Representations. arXiv preprint arXiv:1803.05449","author":"Conneau Alexis","year":"2018","unstructured":"Alexis Conneau and Douwe Kiela. 2018. SentEval: An Evaluation Toolkit for Universal Sentence Representations. arXiv preprint arXiv:1803.05449 (2018)."},{"key":"e_1_3_2_1_15_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_16_1","volume-title":"Condenser: a pre-training architecture for dense retrieval. arXiv preprint arXiv:2104.08253","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao and Jamie Callan. 2021. Condenser: a pre-training architecture for dense retrieval. arXiv preprint arXiv:2104.08253 (2021)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Leo Gao Jonathan Tow Stella Biderman Sid Black Anthony DiPofi Charles Foster Laurence Golding Jeffrey Hsu Kyle McDonell Niklas Muennighoff Jason Phang Laria Reynolds Eric Tang Anish Thite Ben Wang Kevin Wang and Andy Zou. 2021a. A framework for few-shot language model evaluation. https:\/\/doi.org\/10.5281\/zenodo.5371628","DOI":"10.5281\/zenodo.5371628"},{"key":"e_1_3_2_1_18_1","volume-title":"Scaling deep contrastive learning batch size under memory limited setup. arXiv preprint arXiv:2101.06983","author":"Gao Luyu","year":"2021","unstructured":"Luyu Gao, Yunyi Zhang, Jiawei Han, and Jamie Callan. 2021b. Scaling deep contrastive learning batch size under memory limited setup. arXiv preprint arXiv:2101.06983 (2021)."},{"key":"e_1_3_2_1_19_1","volume-title":"International conference on machine learning. PMLR, 3929--3938","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 International conference on machine learning. PMLR, 3929--3938."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Wei He Kai Liu Jing Liu Yajuan Lyu Shiqi Zhao Xinyan Xiao Yuan Liu Yizhong Wang Hua Wu Qiaoqiao She et al. 2017. Dureader: a chinese machine reading comprehension dataset from real-world applications. arXiv preprint arXiv:1711.05073 (2017).","DOI":"10.18653\/v1\/W18-2605"},{"key":"e_1_3_2_1_21_1","volume-title":"Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al.","author":"Hoffmann Jordan","year":"2022","unstructured":"Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al. 2022. Training compute-optimal large language models. arXiv preprint arXiv:2203.15556 (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118 (2021)."},{"key":"e_1_3_2_1_23_1","volume-title":"Few-shot learning with retrieval augmented language models. arXiv preprint arXiv:2208.03299","author":"Izacard Gautier","year":"2022","unstructured":"Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2022. Few-shot learning with retrieval augmented language models. arXiv preprint arXiv:2208.03299 (2022)."},{"key":"e_1_3_2_1_24_1","volume-title":"Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard. arXiv preprint arXiv:2306.07471","author":"Kamalloo Ehsan","year":"2023","unstructured":"Ehsan Kamalloo, Nandan Thakur, Carlos Lassance, Xueguang Ma, Jheng-Hong Yang, and Jimmy Lin. 2023. Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard. arXiv preprint arXiv:2306.07471 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Ouguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)."},{"key":"e_1_3_2_1_26_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, Vol. 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_27_1","volume-title":"Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al.","author":"Li Raymond","year":"2023","unstructured":"Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al. 2023a. StarCoder: may the source be with you! arXiv preprint arXiv:2305.06161 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Towards General Text Embeddings with Multi-stage Contrastive Learning. arXiv preprint arXiv:2308.03281","author":"Li Zehan","year":"2023","unstructured":"Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023b. Towards General Text Embeddings with Multi-stage Contrastive Learning. arXiv preprint arXiv:2308.03281 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_30_1","volume-title":"Retromae: Pre-training retrieval-oriented transformers via masked auto-encoder. arXiv preprint arXiv:2205.12035","author":"Liu Zheng","year":"2022","unstructured":"Zheng Liu and Yingxia Shao. 2022. Retromae: Pre-training retrieval-oriented transformers via masked auto-encoder. arXiv preprint arXiv:2205.12035 (2022)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531736"},{"key":"e_1_3_2_1_32_1","volume-title":"Sgpt: Gpt sentence embeddings for semantic search. arXiv preprint arXiv:2202.08904","author":"Muennighoff Niklas","year":"2022","unstructured":"Niklas Muennighoff. 2022. Sgpt: Gpt sentence embeddings for semantic search. arXiv preprint arXiv:2202.08904 (2022)."},{"key":"e_1_3_2_1_33_1","volume-title":"Swayam Singh, Xiangru Tang, Leandro von Werra, and Shayne Longpre.","author":"Muennighoff Niklas","year":"2023","unstructured":"Niklas Muennighoff, Qian Liu, Armel Zebaze, Qinkai Zheng, Binyuan Hui, Terry Yue Zhuo, Swayam Singh, Xiangru Tang, Leandro von Werra, and Shayne Longpre. 2023a. OctoPack: Instruction Tuning Code Large Language Models. arXiv preprint arXiv:2308.07124 (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"Aleksandra Piktus, Nouamane Tazi, Sampo Pyysalo, Thomas Wolf, and Colin Raffel.","author":"Muennighoff Niklas","year":"2023","unstructured":"Niklas Muennighoff, Alexander M Rush, Boaz Barak, Teven Le Scao, Aleksandra Piktus, Nouamane Tazi, Sampo Pyysalo, Thomas Wolf, and Colin Raffel. 2023b. Scaling Data-Constrained Language Models. arXiv preprint arXiv:2305.16264 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"MTEB: Massive text embedding benchmark. arXiv preprint arXiv:2210.07316","author":"Muennighoff Niklas","year":"2022","unstructured":"Niklas Muennighoff, Nouamane Tazi, Lo\u00efc Magne, and Nils Reimers. 2022a. MTEB: Massive text embedding benchmark. arXiv preprint arXiv:2210.07316 (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"M Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf, et al.","author":"Muennighoff Niklas","year":"2022","unstructured":"Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven Le Scao, M Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf, et al. 2022b. Crosslingual generalization through multitask finetuning. arXiv preprint arXiv:2211.01786 (2022)."},{"key":"e_1_3_2_1_37_1","volume-title":"Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, et al.","author":"Neelakantan Arvind","year":"2022","unstructured":"Arvind Neelakantan, Tao Xu, Raul Puri, Alec Radford, Jesse Michael Han, Jerry Tworek, Qiming Yuan, Nikolas Tezak, Jong Wook Kim, Chris Hallacy, et al. 2022. Text and code embeddings by contrastive pre-training. arXiv preprint arXiv:2201.10005 (2022)."},{"key":"e_1_3_2_1_38_1","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. (2016)."},{"key":"e_1_3_2_1_39_1","volume-title":"Sentence-t5: Scalable sentence encoders from pre-trained text-to-text models. arXiv preprint arXiv:2108.08877","author":"Ni Jianmo","year":"2021","unstructured":"Jianmo Ni, Gustavo Hern\u00e1ndez \u00c1brego, Noah Constant, Ji Ma, Keith B Hall, Daniel Cer, and Yinfei Yang. 2021a. Sentence-t5: Scalable sentence encoders from pre-trained text-to-text models. arXiv preprint arXiv:2108.08877 (2021)."},{"key":"e_1_3_2_1_40_1","unstructured":"Jianmo Ni Chen Qu Jing Lu Zhuyun Dai Gustavo Hern\u00e1ndez \u00c1brego Ji Ma Vincent Y Zhao Yi Luan Keith B Hall Ming-Wei Chang et al. 2021b. Large dual encoders are generalizable retrievers. arXiv preprint arXiv:2112.07899 (2021)."},{"key":"e_1_3_2_1_41_1","unstructured":"Yujia Qin Shihao Liang Yining Ye Kunlun Zhu Lan Yan Yaxi Lu Yankai Lin Xin Cong Xiangru Tang Bill Qian et al. 2023. ToolLLM: Facilitating Large Language Models to Master 16000 Real-world APIs. arXiv preprint arXiv:2307.16789 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine. arXiv preprint arXiv:2203.10232","author":"Qiu Yifu","year":"2022","unstructured":"Yifu Qiu, Hongyu Li, Yingqi Qu, Ying Chen, Qiaoqiao She, Jing Liu, Hua Wu, and Haifeng Wang. 2022. DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine. arXiv preprint arXiv:2203.10232 (2022)."},{"key":"e_1_3_2_1_43_1","volume-title":"Daxiang Dong, Hua Wu, and Haifeng Wang.","author":"Qu Yingqi","year":"2020","unstructured":"Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu, and Haifeng Wang. 2020. RocketQA: An optimized training approach to dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2010.08191 (2020)."},{"key":"e_1_3_2_1_44_1","unstructured":"Jack W Rae Sebastian Borgeaud Trevor Cai Katie Millican Jordan Hoffmann Francis Song John Aslanides Sarah Henderson Roman Ring Susannah Young et al. 2021. Scaling language models: Methods analysis & insights from training gopher. arXiv preprint arXiv:2112.11446 (2021)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_46_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_47_1","volume-title":"Arun Raja, et al.","author":"Sanh Victor","year":"2021","unstructured":"Victor Sanh, Albert Webson, Colin Raffel, Stephen H Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, et al. 2021. Multitask prompted training enables zero-shot task generalization. arXiv preprint arXiv:2110.08207 (2021)."},{"key":"e_1_3_2_1_48_1","volume-title":"Replug: Retrieval-augmented black-box language models. arXiv preprint 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 preprint arXiv:2301.12652 (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"Abubakar Abid, Adam Fisch, Adam R Brown, Adam Santoro, Aditya Gupta, Adri\u00e0 Garriga-Alonso, et al.","author":"Srivastava Aarohi","year":"2022","unstructured":"Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R Brown, Adam Santoro, Aditya Gupta, Adri\u00e0 Garriga-Alonso, et al. 2022. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615 (2022)."},{"key":"e_1_3_2_1_50_1","unstructured":"Hongjin Su Jungo Kasai Yizhong Wang Yushi Hu Mari Ostendorf Wen-tau Yih Noah A Smith Luke Zettlemoyer Tao Yu et al. 2022. One embedder any task: Instruction-finetuned text embeddings. arXiv preprint arXiv:2212.09741 (2022)."},{"key":"e_1_3_2_1_51_1","volume-title":"Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663 (2021)."},{"key":"e_1_3_2_1_52_1","volume-title":"Simlm: Pre-training with representation bottleneck for dense passage retrieval. arXiv preprint arXiv:2207.02578","author":"Wang Liang","year":"2022","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022a. Simlm: Pre-training with representation bottleneck for dense passage retrieval. arXiv preprint arXiv:2207.02578 (2022)."},{"key":"e_1_3_2_1_53_1","volume-title":"Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533","author":"Wang Liang","year":"2022","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022b. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)."},{"key":"e_1_3_2_1_54_1","volume-title":"Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le.","author":"Wei Jason","year":"2021","unstructured":"Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. 2021. Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)."},{"key":"e_1_3_2_1_55_1","volume-title":"A broad-coverage challenge corpus for sentence understanding through inference. arXiv preprint arXiv:1704.05426","author":"Williams Adina","year":"2017","unstructured":"Adina Williams, Nikita Nangia, and Samuel R Bowman. 2017. A broad-coverage challenge corpus for sentence understanding through inference. arXiv preprint arXiv:1704.05426 (2017)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531799"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511957"},{"key":"e_1_3_2_1_58_1","volume-title":"RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models. arXiv preprint arXiv:2305.02564","author":"Xiao Shitao","year":"2023","unstructured":"Shitao Xiao, Zheng Liu, Yingxia Shao, and Zhao Cao. 2023. RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models. arXiv preprint arXiv:2305.02564 (2023)."},{"key":"e_1_3_2_1_59_1","volume-title":"Matching-oriented product quantization for ad-hoc retrieval. arXiv preprint arXiv:2104.07858","author":"Xiao Shitao","year":"2021","unstructured":"Shitao Xiao, Zheng Liu, Yingxia Shao, Defu Lian, and Xing Xie. 2021. Matching-oriented product quantization for ad-hoc retrieval. arXiv preprint arXiv:2104.07858 (2021)."},{"key":"e_1_3_2_1_60_1","unstructured":"Xiaohui Xie Qian Dong Bingning Wang Feiyang Lv Ting Yao Weinan Gan Zhijing Wu Xiangsheng Li Haitao Li Yiqun Liu et al. 2023. T2Ranking: A large-scale Chinese Benchmark for Passage Ranking. arXiv preprint arXiv:2304.03679 (2023)."},{"key":"e_1_3_2_1_61_1","volume-title":"Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808","author":"Xiong Lee","year":"2020","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_1_62_1","volume-title":"CLUE: A Chinese language understanding evaluation benchmark. arXiv preprint arXiv:2004.05986","author":"Xu Liang","year":"2020","unstructured":"Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, et al. 2020. CLUE: A Chinese language understanding evaluation benchmark. arXiv preprint arXiv:2004.05986 (2020)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.06.001"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539212"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2883637"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657878","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:32:50Z","timestamp":1755840770000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":65,"alternative-id":["10.1145\/3626772.3657878","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657878","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}