Unveiling DIME: Reproducibility, Generalizability, and Formal Analysis of Dimension Importance Estimation for Dense Retrieval
Dimension IMportance Estimation (DIME) is a recently proposed technique to enhance ranking effectiveness of dense retrieval models by pruning irrelevant embedding dimensions through Pseudo Relevance Feedback (PRF DIME) or exploiting dense representations of Large Language Model-generated answers (LLM DIME). Despite strong empirical performance, its theoretical foundations and generalizability remain open questions.
Authors
- Antonio Mallia (ORCID: https://orcid.org/0000-0002-7817-6140)
- Fabrizio Silvestri (ORCID: https://orcid.org/0000-0001-7669-9055)
- Cesare Campagnano (ORCID: https://orcid.org/0000-0002-8362-274X)
Institutions
- Sapienza University of Rome (IT)
Publication Details
- Published
- 2025-07-13
- DOI
- https://doi.org/10.1145/3726302.3730318
- Citations
- 1
- Primary Topic
- Machine Learning and Data Classification
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- European Commission