Semantic-Enhanced Differentiable Search Index Inspired by Learning Strategies
Open accessAbstract
Recently, a new paradigm called Differentiable Search Index (DSI) has been proposed for document retrieval, wherein a sequence-to-sequence model is learned to directly map queries to relevant document identifiers. The key idea behind DSI is to fully parameterize traditional ''index-retrieve'' pipelines within a single neural model, by encoding all documents in the corpus into the model parameters. In essence, DSI needs to resolve two major questions: (1) how to assign an identifier to each document, and (2) how to learn the associations between a document and its identifier. In this work, we propose a Semantic-Enhanced DSI model (SE-DSI) motivated by Learning Strategies in the area of Cognitive Psychology. Our approach advances original DSI in two ways: (1) For the document identifier, we take inspiration from Elaboration Strategies in human learning. Specifically, we assign each document an Elaborative Description based on the query generation technique, which is more meaningful than a string of integers in the original DSI; and (2) For the associations between a document and its identifier, we take inspiration from Rehearsal Strategies in human learning. Specifically, we select fine-grained semantic features from a document as Rehearsal Contents to improve document memorization. Both the offline and online experiments show improved retrieval performance over prevailing baselines.
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?
DSI and its variations train pretrained language models on the target corpus and treat the model's parameters as an index of the corpus.
“For instance, DSI and its variations [134-137] have tried to train pretrained language models on the target corpus directly and then treat the model's parameter as a 'index' of the corpus.”
From Foundations of GenIR (2025) · cites this paper as [136]
Cites
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
Rethinking search: making domain experts out of dilettantes
Metzler, D., Tay, Y., Bahri, D., & Najork, M. (2021) · ACM SIGIR Forum · doi:10.1145/3476415.3476428 · Cited by 112 · see citing works
A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt Learning
Chen, J., Zhang, R., Guo, J., de Rijke, M., Liu, Y., Fan, Y., & Cheng, X. (2023) · Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3539618.3591631 · Cited by 32 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
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
Self-citationRecent Advances in Generative Information Retrieval
Tang, Y., Zhang, R., Guo, J., & de Rijke, M. (2023) · Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region · doi:10.1145/3624918.3629547 · Cited by 22 · see citing works
Self-citationGenerative Retrieval for Book Search
Tang, Y., Zhang, R., Guo, J., de Rijke, M., Liu, S., Wang, S., Yin, D., & Cheng, X. (2025) · Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1 · doi:10.1145/3690624.3709435 · Cited by 5 · see citing works
Self-citationRecent 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-citationLightweight and Direct Document Relevance Optimization for Generative Information Retrieval
Mekonnen, K. A., Tang, Y., & de Rijke, M. (2025) · Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3726302.3730023 · Cited by 3 · see citing works
“It has inspired the development of several models, including NCI [56], DSI-QG [72], DSI++ [33], SEAL [4], ULTRON [71], TOME [43], IncDSI [22], RI-POR [62], and PAG [63].”
Self-citationAi, Q., Zhan, J., & Liu, Y. (2025) · arXiv · doi:10.48550/arxiv.2501.02842
“Since the birth of GR, a variety types of document IDs have been proposed, which can be broadly categorized as IDs with explicit tokens [134–136] and IDs with implicit tokens [137, 140, 141].”
- Authors
- Tang, Y., Zhang, R., Guo, J., Chen, J., Zhu, Z., Wang, S., Yin, D., & Cheng, X.
- Affiliations
- Institute of Computing Technology (CN)
- Baidu (China) (CN)
- ORCID
- Venue
- Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
- Publisher
- ACM
- Published
- 2023-08-04
- Pages
- 4904-4913
- OpenAlex
- W4385567756
- Cited by
- 29
- References
- 3
- Citations by year
- 2026: 2 · 2025: 10 · 2024: 13 · 2023: 4
- FWCI
- 7.46
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Lenovo-CAS Joint Lab Youth Scientist Project
- National Natural Science Foundation of China (No. 62006218)
- Youth Innovation Promotion Association CAS (No. 20144310)
- China Scholarship Council (No. 202104910234)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- document retrieval, elaboration strategies, rehearsal strategies, query generation, document identifiers
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
