{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:40:54Z","timestamp":1760488854661,"version":"build-2065373602"},"reference-count":77,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2026,1,31]]},"abstract":"<jats:p>Recent advances in representation learning have enabled neural Information Retrieval (IR) systems to use learned dense representations for queries and documents to effectively handle semantics, language nuances, and vocabulary mismatch problems. In contrast to traditional IR systems that rely on word matching, dense IR models exploit query\/document similarity in dense latent spaces to account for semantics. This requires substantial training data and comes with increased computational demands. Thus, it would be beneficial to predict how a system will perform for a given query to decide whether a dense IR model is the best option or alternatives should be used. Traditional Query Performance Prediction (QPP) models are designed for lexical IR approaches and perform sub-optimally when applied to dense neural IR systems. Therefore, there has been a renewed interest in QPP methods to improve their effectiveness for dense neural IR models. While the results of the new QPP methods are generally encouraging, there is ample room for improvement in absolute performance and stability. We argue that by using features more aligned with the underlying rationale of dense IR models, we can enhance the performance of QPP. In this respect, we propose the Projection-Displacement-Based QPP (PDQPP), which exploits the geometric properties of dense IR models, projects queries and retrieved documents onto subspaces defined by pseudo-relevant documents, and considers changes in retrieval scores within them as a proxy for retrieval coherence. Minor score changes suggest robust and coherent retrieval, while significant alterations indicate semantic divergence and potentially poor performance. Results over a wide range of experimental settings on both traditional (TREC Robust) and neural-oriented (TREC Deep Learning) test collections show that PDQPP mostly outperforms the state-of-the-art QPP baselines.<\/jats:p>","DOI":"10.1145\/3765617","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T13:17:56Z","timestamp":1756819076000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Projection-Displacement-Based Query Performance Prediction for Embedded Space of Dense Retrievers"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9220-6652","authenticated-orcid":false,"given":"Suchana","family":"Datta","sequence":"first","affiliation":[{"name":"University College Dublin, Dublin, Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-2049","authenticated-orcid":false,"given":"Guglielmo","family":"Faggioli","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Padua, Padova, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9219-6239","authenticated-orcid":false,"given":"Nicola","family":"Ferro","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Padua, Padova, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0050-7138","authenticated-orcid":false,"given":"Debasis","family":"Ganguly","sequence":"additional","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5265-1831","authenticated-orcid":false,"given":"Cristina Ioana","family":"Muntean","sequence":"additional","affiliation":[{"name":"HPC Lab, Consiglio Nazionale delle Ricerche Istituto di Scienza e Tecnologie dell\u2019Informazione Alessandro Faedo, Pisa, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7189-4724","authenticated-orcid":false,"given":"Raffaele","family":"Perego","sequence":"additional","affiliation":[{"name":"HPC Lab, Consiglio Nazionale delle Ricerche Istituto di Scienza e Tecnologie dell\u2019Informazione Alessandro Faedo, Pisa, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7427-1001","authenticated-orcid":false,"given":"Nicola","family":"Tonellotto","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Pisa, Pisa, Italy"}]}],"member":"320","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_2_2","DOI":"10.1145\/3459637.3482063"},{"doi-asserted-by":"publisher","key":"e_1_3_2_3_2","DOI":"10.1007\/978-3-031-56069-9_51"},{"doi-asserted-by":"publisher","key":"e_1_3_2_4_2","DOI":"10.1145\/3583780.3615270"},{"doi-asserted-by":"publisher","key":"e_1_3_2_5_2","DOI":"10.1145\/3511808.3557719"},{"doi-asserted-by":"publisher","key":"e_1_3_2_6_2","DOI":"10.1016\/j.ipm.2020.102248"},{"doi-asserted-by":"publisher","key":"e_1_3_2_7_2","DOI":"10.1007\/978-3-030-45442-5_10"},{"doi-asserted-by":"publisher","key":"e_1_3_2_8_2","DOI":"10.2200\/S00235ED1V01Y201004ICR015"},{"doi-asserted-by":"publisher","key":"e_1_3_2_9_2","DOI":"10.1145\/3340531.3412032"},{"doi-asserted-by":"publisher","key":"e_1_3_2_10_2","DOI":"10.1007\/978-3-030-99739-7_8"},{"doi-asserted-by":"publisher","key":"e_1_3_2_11_2","DOI":"10.1145\/290941.291009"},{"doi-asserted-by":"crossref","unstructured":"Nick Craswell Bhaskar Mitra Emine Yilmaz and Daniel Campos. 2021. Overview of the TREC 2020 deep learning track. arXiv:2102.07662. Retrieved from https:\/\/arxiv.org\/abs\/2102.07662","key":"e_1_3_2_12_2","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"doi-asserted-by":"crossref","unstructured":"Nick Craswell Bhaskar Mitra Emine Yilmaz Daniel Campos and Ellen M. Voorhees. 2020. Overview of the TREC 2019 deep learning track. arXiv:2003.07820. Retrieved from https:\/\/arxiv.org\/abs\/2003.07820","key":"e_1_3_2_13_2","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"doi-asserted-by":"publisher","key":"e_1_3_2_14_2","DOI":"10.1145\/564376.564429"},{"doi-asserted-by":"publisher","key":"e_1_3_2_15_2","DOI":"10.1145\/2009916.2010063"},{"doi-asserted-by":"publisher","key":"e_1_3_2_16_2","DOI":"10.1145\/3159652.3159659"},{"doi-asserted-by":"publisher","key":"e_1_3_2_17_2","DOI":"10.1145\/3488560.3498491"},{"doi-asserted-by":"publisher","key":"e_1_3_2_18_2","DOI":"10.1007\/978-3-031-56060-6_13"},{"doi-asserted-by":"publisher","unstructured":"Suchana Datta Debasis Ganguly Mandar Mitra and Derek Greene. 2023. A relative information gain-based query performance prediction framework with generated query variants. ACM Transactions on Information Systems 41 2 Article 38 (2023) 1\u201331. DOI: 10.1145\/3545112","key":"e_1_3_2_19_2","DOI":"10.1145\/3545112"},{"doi-asserted-by":"publisher","key":"e_1_3_2_20_2","DOI":"10.1145\/3477495.3531821"},{"doi-asserted-by":"publisher","key":"e_1_3_2_21_2","DOI":"10.18653\/v1\/n19-1423"},{"doi-asserted-by":"publisher","key":"e_1_3_2_22_2","DOI":"10.1007\/978-3-031-56066-8_6"},{"doi-asserted-by":"publisher","key":"e_1_3_2_23_2","DOI":"10.1007\/978-3-031-28241-6_42"},{"doi-asserted-by":"publisher","key":"e_1_3_2_24_2","DOI":"10.1007\/978-3-031-28241-6_42"},{"doi-asserted-by":"publisher","key":"e_1_3_2_25_2","DOI":"10.1145\/3539618.3591625"},{"doi-asserted-by":"publisher","key":"e_1_3_2_26_2","DOI":"10.1145\/3578337.3605142"},{"doi-asserted-by":"publisher","key":"e_1_3_2_27_2","DOI":"10.48550\/ARXIV.2302.09947"},{"doi-asserted-by":"publisher","key":"e_1_3_2_28_2","DOI":"10.1007\/978-3-030-72113-8_8"},{"doi-asserted-by":"publisher","unstructured":"Guglielmo Faggioli Oleg Zendel J. Shane Culpepper Nicola Ferro and Falk Scholer. 2022. sMARE: A new paradigm to evaluate and understand query performance prediction methods. Information Retrieval Journal 25 2 (2022) 94\u2013122. DOI: 10.1007\/s10791-022-09407-w","key":"e_1_3_2_29_2","DOI":"10.1007\/s10791-022-09407-w"},{"key":"e_1_3_2_30_2","first-page":"215","volume-title":"Proceedings of the Advances in Information Retrieval\u201444th European Conference on IR Research (ECIR \u201922)","author":"Ganguly Debasis","year":"2022","unstructured":"Debasis Ganguly, Suchana Datta, Mandar Mitra, and Derek Greene. 2022. An analysis of variations in the effectiveness of query performance prediction. In Proceedings of the Advances in Information Retrieval\u201444th European Conference on IR Research (ECIR \u201922). Lecture Notes in Computer Science, Vol. 13185, Springer, 215\u2013229."},{"doi-asserted-by":"publisher","key":"e_1_3_2_31_2","DOI":"10.1007\/978-3-030-99736-6_15"},{"doi-asserted-by":"crossref","unstructured":"Debasis Ganguly and Emine Yilmaz. 2023. Query-specific variable depth pooling via query performance prediction towards reducing relevance assessment effort. arXiv:2304.11752. Retrieved from https:\/\/arxiv.org\/abs\/2304.11752","key":"e_1_3_2_32_2","DOI":"10.1145\/3539618.3592046"},{"doi-asserted-by":"publisher","key":"e_1_3_2_33_2","DOI":"10.1145\/2983323.2983769"},{"doi-asserted-by":"publisher","key":"e_1_3_2_34_2","DOI":"10.1145\/3341981.3344249"},{"doi-asserted-by":"publisher","key":"e_1_3_2_35_2","DOI":"10.1145\/1842890.1842906"},{"doi-asserted-by":"publisher","key":"e_1_3_2_36_2","DOI":"10.1145\/1458082.1458311"},{"doi-asserted-by":"publisher","key":"e_1_3_2_37_2","DOI":"10.1145\/3404835.3462891"},{"issue":"2","key":"e_1_3_2_38_2","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm Sture","year":"1979","unstructured":"Sture Holm. 1979. A simple sequentially rejective multiple test procedure. Scandinavian Journal of Statistics 6, 2 (1979), 65\u201370. Retrieved from http:\/\/www.jstor.org\/stable\/4615733","journal-title":"Scandinavian Journal of Statistics"},{"unstructured":"Gautier Izacard Mathilde Caron Lucas Hosseini Sebastian Riedel Piotr Bojanowski Armand Joulin and Edouard Grave. 2021. Towards unsupervised dense information retrieval with contrastive learning. arXiv:2112.09118. Retrieved from https:\/\/arxiv.org\/abs\/2112.09118","key":"e_1_3_2_39_2"},{"doi-asserted-by":"publisher","key":"e_1_3_2_40_2","DOI":"10.1145\/3397271.3401075"},{"doi-asserted-by":"publisher","key":"e_1_3_2_41_2","DOI":"10.1016\/j.ipm.2020.102399"},{"doi-asserted-by":"publisher","key":"e_1_3_2_42_2","DOI":"10.1007\/978-3-031-56063-7_27"},{"doi-asserted-by":"publisher","key":"e_1_3_2_43_2","DOI":"10.1162\/tacl_a_00369"},{"doi-asserted-by":"publisher","key":"e_1_3_2_44_2","DOI":"10.1145\/3404835.3463262"},{"doi-asserted-by":"publisher","key":"e_1_3_2_45_2","DOI":"10.1016\/J.IPM.2019.102109"},{"key":"e_1_3_2_46_2","volume-title":"Proceedings of the 1st International Conference on Learning Representations (ICLR \u201913)","author":"Mikolov Tom\u00e1s","year":"2013","unstructured":"Tom\u00e1s Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. In Proceedings of the 1st International Conference on Learning Representations (ICLR \u201913). Workshop Track Proceedings. Retrieved from http:\/\/arxiv.org\/abs\/1301.3781"},{"key":"e_1_3_2_47_2","first-page":"7","volume-title":"ACM Conference on Research and Development in Information Retrieval, SIGIR, Predicting Query Difficulty\u2014Methods and Applications Workshop","author":"Mothe Josiane","year":"2005","unstructured":"Josiane Mothe and Ludovic Tanguy. 2005. Linguistic features to predict query difficulty. In Proceedings of the ACM Conference on Research and Development in Information Retrieval, SIGIR, Predicting Query Difficulty\u2014Methods and Applications Workshop, 7\u201310."},{"key":"e_1_3_2_48_2","volume-title":"Proceedings of the Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches 2016 Co-Located with the 30th Annual Conference on Neural Information Processing Systems (NIPS \u201916)","volume":"1773","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A human generated MAchine reading COmprehension dataset. In Proceedings of the Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches 2016 Co-Located with the 30th Annual Conference on Neural Information Processing Systems (NIPS \u201916). Tarek Richard Besold, Antoine Bordes, Artur S. d\u2019Avila Garcez, and Greg Wayne (Eds.), CEUR Workshop Proceedings, Vol. 1773, CEUR-WS.org. Retrieved from https:\/\/ceur-ws.org\/Vol-1773\/CoCoNIPS_2016_paper9.pdf"},{"unstructured":"Rodrigo Frassetto Nogueira Wei Yang Kyunghyun Cho and Jimmy Lin. 2019. Multi-stage document ranking with BERT. arXiv:1910.14424. Retrieved from http:\/\/arxiv.org\/abs\/1910.14424","key":"e_1_3_2_49_2"},{"unstructured":"Rodrigo Frassetto Nogueira Wei Yang Jimmy Lin and Kyunghyun Cho. 2019. Document expansion by query prediction. arXiv:1904.08375. Retrieved from http:\/\/arxiv.org\/abs\/1904.08375","key":"e_1_3_2_50_2"},{"doi-asserted-by":"publisher","key":"e_1_3_2_51_2","DOI":"10.1007\/978-3-642-16321-0_21"},{"unstructured":"Yifan Qiao Chenyan Xiong Zhenghao Liu and Zhiyuan Liu. 2019. Understanding the behaviors of BERT in ranking. arXiv:1904.07531. Retrieved from http:\/\/arxiv.org\/abs\/1904.07531","key":"e_1_3_2_52_2"},{"key":"e_1_3_2_53_2","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML \u201921)","volume":"139","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning transferable visual models from natural language supervision. In Proceedings of the 38th International Conference on Machine Learning (ICML \u201921), Virtual Event. Marina Meila and Tong Zhang (Eds.), Proceedings of Machine Learning Research, Vol. 139, PMLR, 8748\u20138763. Retrieved from http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"doi-asserted-by":"publisher","key":"e_1_3_2_54_2","DOI":"10.1145\/2600428.2609581"},{"doi-asserted-by":"publisher","key":"e_1_3_2_55_2","DOI":"10.1561\/1500000019"},{"doi-asserted-by":"publisher","key":"e_1_3_2_56_2","DOI":"10.1145\/3077136.3080665"},{"doi-asserted-by":"publisher","key":"e_1_3_2_57_2","DOI":"10.1145\/3331184.3331334"},{"doi-asserted-by":"publisher","key":"e_1_3_2_58_2","DOI":"10.1145\/3121050.3121087"},{"doi-asserted-by":"publisher","key":"e_1_3_2_59_2","DOI":"10.1016\/j.ipm.2018.10.009"},{"doi-asserted-by":"publisher","key":"e_1_3_2_60_2","DOI":"10.1007\/978-3-031-56066-8_4"},{"doi-asserted-by":"publisher","key":"e_1_3_2_61_2","DOI":"10.1145\/1835449.1835494"},{"doi-asserted-by":"publisher","unstructured":"Anna Shtok Oren Kurland and David Carmel. 2016. Query performance prediction using reference lists. ACM Transactions on Information Systems 34 4 Article 19 (2016) 1\u201334. DOI: 10.1145\/2926790","key":"e_1_3_2_62_2","DOI":"10.1145\/2926790"},{"doi-asserted-by":"publisher","unstructured":"Anna Shtok Oren Kurland David Carmel Fiana Raiber and Gad Markovits. 2012. Predicting query performance by query-drift estimation. ACM Transactions on Information Systems 30 2 Article 11 (2012) 1\u201335. DOI: 10.1145\/2180868.2180873","key":"e_1_3_2_63_2","DOI":"10.1145\/2180868.2180873"},{"doi-asserted-by":"publisher","key":"e_1_3_2_64_2","DOI":"10.1145\/3539618.3592082"},{"doi-asserted-by":"publisher","key":"e_1_3_2_65_2","DOI":"10.1145\/2661829.2661906"},{"doi-asserted-by":"publisher","key":"e_1_3_2_66_2","DOI":"10.2307\/3001913"},{"key":"e_1_3_2_67_2","volume-title":"Information Retrieval","author":"van Rijsbergen C. J.","year":"1979","unstructured":"C. J. van Rijsbergen. 1979. Information Retrieval. Butterworth."},{"doi-asserted-by":"publisher","unstructured":"Ellen Voorhees. 2005. Overview of the TREC 2004 Robust Retrieval Track. Special Publication (NIST SP) National Institute of Standards and Technology Gaithersburg MD [online]. Retrieved September 11 2025 from 10.6028\/NIST.SP.500-261","key":"e_1_3_2_68_2","DOI":"10.6028\/NIST.SP.500-261"},{"key":"e_1_3_2_69_2","volume-title":"in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 (NeurIPS \u201920), Virtual Event","author":"Wang Wenhui","year":"2020","unstructured":"Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. MiniLM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. In Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 (NeurIPS \u201920), Virtual Event. Hugo Larochelle, Marc\u2019Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). Retrieved from https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"doi-asserted-by":"publisher","key":"e_1_3_2_70_2","DOI":"10.2307\/3001968"},{"key":"e_1_3_2_71_2","volume-title":"9th International Conference on Learning Representations (ICLR \u201921)","author":"Xiong Lee","year":"2021","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In Proceedings of the 9th International Conference on Learning Representations (ICLR \u201921), Virtual Event. OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=zeFrfgyZln"},{"doi-asserted-by":"publisher","key":"e_1_3_2_72_2","DOI":"10.1145\/2983323.2983818"},{"doi-asserted-by":"publisher","key":"e_1_3_2_73_2","DOI":"10.1145\/3209978.3210041"},{"doi-asserted-by":"publisher","key":"e_1_3_2_74_2","DOI":"10.1145\/3331184.3331253"},{"doi-asserted-by":"publisher","key":"e_1_3_2_75_2","DOI":"10.1145\/3404835.3462880"},{"unstructured":"Wayne Xin Zhao Jing Liu Ruiyang Ren and Ji-Rong Wen. 2022. Dense text retrieval based on pretrained language models: A survey. arXiv:2211.14876. Retrieved from https:\/\/arxiv.org\/abs\/2211.14876","key":"e_1_3_2_76_2"},{"doi-asserted-by":"publisher","key":"e_1_3_2_77_2","DOI":"10.1007\/978-3-540-78646-7_8"},{"doi-asserted-by":"publisher","key":"e_1_3_2_78_2","DOI":"10.1145\/1277741.1277835"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3765617","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T18:31:25Z","timestamp":1760466685000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3765617"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,14]]},"references-count":77,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,31]]}},"alternative-id":["10.1145\/3765617"],"URL":"https:\/\/doi.org\/10.1145\/3765617","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"type":"print","value":"1046-8188"},{"type":"electronic","value":"1558-2868"}],"subject":[],"published":{"date-parts":[[2025,10,14]]},"assertion":[{"value":"2024-04-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}