Generative Retrieval as Multi-Vector Dense Retrieval
Open accessAbstract
Generative retrieval generates identifiers of relevant documents in an end-to-end manner using a sequence-to-sequence architecture for a given query. The relation between generative retrieval and other retrieval methods, especially those based on matching within dense retrieval models, is not yet fully comprehended. Prior work has demonstrated that generative retrieval with atomic identifiers is equivalent to single-vector dense retrieval. Accordingly, generative retrieval exhibits behavior analogous to hierarchical search within a tree index in dense retrieval when using hierarchical semantic identifiers. However, prior work focuses solely on the retrieval stage without considering the deep interactions within the decoder of generative retrieval. In this paper, we fill this gap by demonstrating that generative retrieval and multi-vector dense retrieval share the same framework for measuring the relevance to a query of a document. Specifically, we examine the attention layer and prediction head of generative retrieval, revealing that generative retrieval can be understood as a special case of multi-vector dense retrieval. Both methods compute relevance as a sum of products of query and document vectors and an alignment matrix. We then explore how generative retrieval applies this framework, employing distinct strategies for computing document token vectors and the alignment matrix. We have conducted experiments to verify our conclusions and show that both paradigms exhibit commonalities of term matching in their alignment matrix.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Wu et al. proved that GR models with implicit tokens are equal to multi-vector dense retrieval models in theory.
“Wu et al. [142] have proved that the GR models with implicit tokens are equal to a multi-vector dense retrieval models in theory.”
From Foundations of GenIR (2025) · cites this paper as [142]
Cites
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · see citing works
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821 · see citing works
Dense passage retrieval for open-domain question answering
Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-T. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.550 · Cited by 3,575 · see citing works
Natural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069 · see citing works
ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
Khattab, O., & Zaharia, M. (2020) · Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3397271.3401075 · Cited by 1,301 · see citing works
Sparse, Dense, and Attentional Representations for Text Retrieval
Luan, Y., Eisenstein, J., Toutanova, K., & Collins, M. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00369 · Cited by 363 · see citing works
Continual Learning for Generative Retrieval over Dynamic Corpora
Chen, J., Zhang, R., Guo, J., de Rijke, M., Chen, W., Fan, Y., & Cheng, X. (2023) · Proceedings of the 32nd ACM International Conference on Information and Knowledge Management · doi:10.1145/3583780.3614821 · Cited by 40 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Kazi, S., Khoja, S., & Daud, A. (2025) · Computer Science Review · doi:10.1016/j.cosrev.2025.100756 · Cited by 9 · see citing works
Recent Advances in Generative Information Retrieval
Tang, Y., Zhang, R., Ren, Z., Guo, J., & de Rijke, M. (2024) · Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3626772.3661379 · Cited by 4 · see citing works
Self-citationAi, Q., Zhan, J., & Liu, Y. (2025) · arXiv · doi:10.48550/arxiv.2501.02842
“Wu et al. [142] have proved that the GR models with implicit tokens are equal to a multi-vector dense retrieval models in theory.”
- Authors
- Wu, S., Wei, W., Zhang, M., Chen, Z., Ma, J., Ren, Z., de Rijke, M., & Ren, P.
- Affiliations
- Shandong University (CN)
- Leiden University (NL)
- University of Amsterdam, Amsterdam, Netherlands
- ORCID
- Venue
- Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval
- Publisher
- ACM
- Published
- 2024-07-10
- Pages
- 1828-1838
- OpenAlex
- W4400524784
- Cited by
- 15
- References
- 7
- Citations by year
- 2026: 6 · 2025: 6 · 2024: 3
- FWCI
- 3.10
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- Leiden Repository (Leiden University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- Natural Science Foundation of China (62102234, 62372275, 62272274, 62202271, T2293773, 62072279)
- Fairness and Intersectional Non-Discrimination in Human Recommendation (No 101070212)
- LESSEN (NWA.1389.20.183)
- Natural Science Foundation of Shandong Province (ZR2021QF129)
- Hybrid Intelligence Center
- National Key R&D Program of China (No.2022YFC3303004)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- generative retrieval, dense retrieval, generative models, vector retrieval
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
