Abstract:Dense retrievers powered by pretrained embeddings are widely used for document retrieval but struggle in specialized domains due to the mismatches between the training and target domain distributions. Domain adaptation typically requires costly annotation and retraining of query-document pairs. In this work, we revisit an overlooked alternative: applying PCA to domain embeddings to derive lower-dimensional representations that preserve domain-relevant features while discarding non-discriminative components. Though traditionally used for efficiency, we demonstrate that this simple embedding compression can effectively improve retrieval performance. Evaluated across 9 retrievers and 14 MTEB datasets, PCA applied solely to query embeddings improves NDCG@10 in 75.4% of model-dataset pairs, offering a simple and lightweight method for domain adaptation.
From: Chunsheng Zuo [view email]
[v1]
Tue, 20 Jan 2026 02:21:03 UTC (7,425 KB)
[v2]
Tue, 2 Jun 2026 20:16:26 UTC (7,423 KB)
[v3]
Tue, 14 Jul 2026 15:13:23 UTC (7,426 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。