Unveiling DIME: Reproducibility, Generalizability, and Formal Analysis of Dimension Importance Estimation for Dense Retrieval
Cesare Campagnano, Antonio Mallia, Fabrizio Silvestri · 2025
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.