{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:09:01Z","timestamp":1755907741003,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0109400"],"award-info":[{"award-number":["2020AAA0109400"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,26]]},"DOI":"10.1145\/3624918.3625330","type":"proceedings-article","created":{"date-parts":[[2023,11,23]],"date-time":"2023-11-23T08:49:17Z","timestamp":1700729357000},"page":"223-233","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Selecting which Dense Retriever to use for Zero-Shot Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7531-4491","authenticated-orcid":false,"given":"Ekaterina","family":"Khramtsova","sequence":"first","affiliation":[{"name":"University of Queensland, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6711-0955","authenticated-orcid":false,"given":"Shengyao","family":"Zhuang","sequence":"additional","affiliation":[{"name":"The University of Queensland, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5255-8194","authenticated-orcid":false,"given":"Mahsa","family":"Baktashmotlagh","sequence":"additional","affiliation":[{"name":"University of Queensland, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1724-7694","authenticated-orcid":false,"given":"Xi","family":"Wang","sequence":"additional","affiliation":[{"name":"Neusoft, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0271-5563","authenticated-orcid":false,"given":"Guido","family":"Zuccon","sequence":"additional","affiliation":[{"name":"The University of Queensland, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,11,26]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076042"},{"key":"e_1_3_2_1_2_1","unstructured":"Tolga Birdal Aaron Lou Leonidas\u00a0J. Guibas and Umut cSimcsekli. 2021. Intrinsic Dimension Persistent Homology and Generalization in Neural Networks. In NeurIPS."},{"key":"e_1_3_2_1_3_1","volume-title":"Inpars: Data augmentation for information retrieval using large language models. arXiv preprint arXiv:2202.05144","author":"Bonifacio Luiz","year":"2022","unstructured":"Luiz Bonifacio, Hugo Abonizio, Marzieh Fadaee, and Rodrigo Nogueira. 2022. Inpars: Data augmentation for information retrieval using large language models. arXiv preprint arXiv:2202.05144 (2022)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2348283.2348540"},{"key":"e_1_3_2_1_5_1","unstructured":"Jiefeng Chen Frederick Liu Besim Avci Xi Wu Yingyu Liang and Somesh Jha. 2021. Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99736-6_7"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Min\u00a0Jin Chong and David\u00a0A. Forsyth. 2020. Effectively Unbiased FID and Inception Score and Where to Find Them. (2020) 6069\u20136078.","DOI":"10.1109\/CVPR42600.2020.00611"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Min\u00a0Jin Chong and David\u00a0A. Forsyth. 2020. Effectively Unbiased FID and Inception Score and Where to Find Them. (2020) 6069\u20136078.","DOI":"10.1109\/CVPR42600.2020.00611"},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference of Machine Learning (ICML)","author":"Chuang Ching-Yao","year":"2020","unstructured":"Ching-Yao Chuang, Antonio Torralba, and Stefanie Jegelka. 2020. Estimating Generalization under Distribution Shifts via Domain-Invariant Representations. International Conference of Machine Learning (ICML) (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277795"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00489"},{"volume-title":"Information retrieval: Uncertainty and logics: Uncertainty and logics: Advanced models for the representation and retrieval of information. Vol.\u00a04","author":"Crestani Fabio","key":"e_1_3_2_1_12_1","unstructured":"Fabio Crestani, Mounia Lalmas, and Cornelis\u00a0Joost van Rijsbergen. 1998. Information retrieval: Uncertainty and logics: Uncertainty and logics: Advanced models for the representation and retrieval of information. Vol.\u00a04. Springer Science & Business Media."},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference of Machine Learning (ICML).","author":"Deng Weijian","year":"2021","unstructured":"Weijian Deng, Stephen Gould, and Liang Zheng. 2021. What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?. In International Conference of Machine Learning (ICML)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01482"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.75"},{"key":"e_1_3_2_1_16_1","volume-title":"Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval. ArXiv abs\/2203.05765","author":"Gao Luyu","year":"2022","unstructured":"Luyu Gao, Xueguang Ma, Jimmy\u00a0J. Lin, and Jamie Callan. 2022. Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval. ArXiv abs\/2203.05765 (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Learning Representations, ICLR. https:\/\/arxiv.org\/abs\/2201","author":"Garg Saurabh","year":"2022","unstructured":"Saurabh Garg, Sivaraman Balakrishnan, Zachary\u00a0Chase Lipton, Behnam Neyshabur, and Hanie Sedghi. 2022. Leveraging Unlabeled Data to Predict Out-of-Distribution Performance. In International Conference on Learning Representations, ICLR. https:\/\/arxiv.org\/abs\/2201.04234"},{"key":"e_1_3_2_1_18_1","volume-title":"Predicting with Confidence on Unseen Distributions. IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Guillory Devin","year":"2021","unstructured":"Devin Guillory, Vaishaal Shankar, Sayna Ebrahimi, Trevor Darrell, and Ludwig Schmidt. 2021. Predicting with Confidence on Unseen Distributions. IEEE\/CVF International Conference on Computer Vision (ICCV) (2021), 1114\u20131124."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1458082.1458311"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2005.11.003"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of International Conference on Learning Representations","author":"Hendrycks Dan","year":"2017","unstructured":"Dan Hendrycks and Kevin Gimpel. 2017. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks. Proceedings of International Conference on Learning Representations (2017)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462891"},{"key":"e_1_3_2_1_24_1","unstructured":"Gautier Izacard Mathilde Caron Lucas Hosseini Sebastian Riedel Piotr Bojanowski Armand Joulin and Edouard Grave. [n.d.]. Unsupervised Dense Information Retrieval with Contrastive Learning. Transactions on Machine Learning Research ([n. d.])."},{"key":"e_1_3_2_1_25_1","volume-title":"InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval. arXiv preprint arXiv:2301.01820","author":"Jeronymo Vitor","year":"2023","unstructured":"Vitor Jeronymo, Luiz Bonifacio, Hugo Abonizio, Marzieh Fadaee, Roberto Lotufo, Jakub Zavrel, and Rodrigo Nogueira. 2023. InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrieval. arXiv preprint arXiv:2301.01820 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Predicting the Generalization Gap in Deep Networks with Margin Distributions. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HJlQfnCqKX","author":"Jiang Yiding","year":"2019","unstructured":"Yiding Jiang, Dilip Krishnan, Hossein Mobahi, and Samy Bengio. 2019. Predicting the Generalization Gap in Deep Networks with Margin Distributions. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HJlQfnCqKX"},{"key":"e_1_3_2_1_27_1","volume-title":"Assessing Generalization of SGD via Disagreement. ArXiv abs\/2106.13799","author":"Jiang Yiding","year":"2022","unstructured":"Yiding Jiang, Vaishnavh Nagarajan, Christina Baek, and J.\u00a0Zico Kolter. 2022. Assessing Generalization of SGD via Disagreement. ArXiv abs\/2106.13799 (2022)."},{"key":"e_1_3_2_1_28_1","volume-title":"Weight-Based Performance Estimation for Diverse Domains. arXiv preprint","author":"Khratmtsova Ekaterina","year":"2023","unstructured":"Ekaterina Khratmtsova, Guido Zuccon, Wang Xi, and Mahsa Baktashmotlagh. 2023. Weight-Based Performance Estimation for Diverse Domains. arXiv preprint (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs. In IJCAI.","author":"Lacombe Th\u00e9o","year":"2021","unstructured":"Th\u00e9o Lacombe, Yuichi Ike, and Yuhei Umeda. 2021. Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs. In IJCAI."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3471158.3472229"},{"key":"e_1_3_2_1_31_1","volume-title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval. arXiv preprint arXiv:2302.07452","author":"Lin Sheng-Chieh","year":"2023","unstructured":"Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, and Xilun Chen. 2023. How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval. arXiv preprint arXiv:2302.07452 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.92"},{"key":"e_1_3_2_1_33_1","unstructured":"John Miller Rohan Taori Aditi Raghunathan Shiori Sagawa Pang\u00a0Wei Koh Vaishaal Shankar Percy Liang Yair Carmon and Ludwig Schmidt. 2021. Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization. (2021)."},{"key":"e_1_3_2_1_34_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. choice 2640","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. choice 2640 (2016), 660."},{"key":"e_1_3_2_1_35_1","unstructured":"Rodrigo Nogueira and Jimmy Lin. 2019. From doc2query to docTTTTTquery."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609581"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_38_1","volume-title":"A thorough examination on zero-shot dense retrieval. arXiv preprint arXiv:2204.12755","author":"Ren Ruiyang","year":"2022","unstructured":"Ruiyang Ren, Yingqi Qu, Jing Liu, Wayne\u00a0Xin Zhao, Qifei Wu, Yuchen Ding, Hua Wu, Haifeng Wang, and Ji-Rong Wen. 2022. A thorough examination on zero-shot dense retrieval. arXiv preprint arXiv:2204.12755 (2022)."},{"key":"e_1_3_2_1_39_1","volume-title":"Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology. In International Conference on Learning Representations.","author":"Rieck Bastian","year":"2019","unstructured":"Bastian Rieck, Matteo Togninalli, Christian Bock, Michael Moor, Max Horn, Thomas Gumbsch, and Karsten Borgwardt. 2019. Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology. In International Conference on Learning Representations."},{"volume-title":"IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE Computer Society, 9164\u20139173","author":"Saito K.","key":"e_1_3_2_1_40_1","unstructured":"K. Saito, D. Kim, P. Teterwak, S. Sclaroff, T. Darrell, and K. Saenko. 2021. Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density. In IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE Computer Society, 9164\u20139173."},{"key":"e_1_3_2_1_41_1","volume-title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_1_42_1","volume-title":"Uncertainty in information retrieval systems. Uncertainty management in information systems: from needs to solutions","author":"Turtle R","year":"1997","unstructured":"Howard\u00a0R Turtle and W\u00a0Bruce Croft. 1997. Uncertainty in information retrieval systems. Uncertainty management in information systems: from needs to solutions (1997), 189\u2013224."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1571963"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.168"},{"key":"e_1_3_2_1_45_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. 2022. SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval. arXiv preprint arXiv:2207.02578 (2022)."},{"volume-title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In International Conference on Learning Representations.","author":"Xiong Lee","key":"e_1_3_2_1_46_1","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul\u00a0N Bennett, Junaid Ahmed, and Arnold Overwijk. [n.d.]. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441667"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390435"},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). Vol.\u00a097","author":"You Kaichao","year":"2019","unstructured":"Kaichao You, Ximei Wang, Mingsheng Long, and Michael Jordan. 2019. Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation. In Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). Vol.\u00a097. PMLR, 7124\u20137133. https:\/\/proceedings.mlr.press\/v97\/you19a.html"},{"key":"e_1_3_2_1_50_1","volume-title":"Dense text retrieval based on pretrained language models: A survey. arXiv preprint arXiv:2211.14876","author":"Zhao Wayne\u00a0Xin","year":"2022","unstructured":"Wayne\u00a0Xin Zhao, Jing Liu, Ruiyang Ren, and Ji-Rong Wen. 2022. Dense text retrieval based on pretrained language models: A survey. arXiv preprint arXiv:2211.14876 (2022)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277835"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1571961"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.225"},{"volume-title":"CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos(SIGIR \u201922)","author":"Zhuang Shengyao","key":"e_1_3_2_1_54_1","unstructured":"Shengyao Zhuang and Guido Zuccon. 2022. CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos(SIGIR \u201922). Association for Computing Machinery, New York, NY, USA, 1444\u20131454."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04417-5_21"}],"event":{"name":"SIGIR-AP '23: Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Beijing China","acronym":"SIGIR-AP '23"},"container-title":["Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624918.3625330","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624918.3625330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T21:32:52Z","timestamp":1755898372000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624918.3625330"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,26]]},"references-count":55,"alternative-id":["10.1145\/3624918.3625330","10.1145\/3624918"],"URL":"https:\/\/doi.org\/10.1145\/3624918.3625330","relation":{},"subject":[],"published":{"date-parts":[[2023,11,26]]},"assertion":[{"value":"2023-11-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}