Alleviating Performance Degradation Caused by Out-of-Distribution Issues in Embedding-Based Retrieval
Haotong Bao, Jianjin Zhang, Qi Chen, Weihao Han, Zhengxin Zeng, Ruiheng Chang, Mingzheng Li, Hao Sun
Abstract
In Embedding Based Retrieval (EBR), Approximate Nearest Neighbor (ANN) algorithms are widely adopted for efficient large-scale search. However, recent studies reveal a query out-of-distribution (OOD) issue, where query and base embeddings follow mismatched distributions, significantly degrading ANN performance. In this work, we empirically verify the generality of this phenomenon and provide a quantitative analysis. To mitigate the distributional gap, we introduce a distribution regularizer into the encoder training objective, encouraging alignment between query and base embeddings. Extensive experiments across multiple datasets, encoders, and ANN indices show that our method consistently improves retrieval performance.
BibTeX
@inproceedings{emnlp2025_alleviatingperfo,
title = {Alleviating Performance Degradation Caused by Out-of-Distribution Issues in Embedding-Based Retrieval},
author = {Haotong Bao and Jianjin Zhang and Qi Chen and Weihao Han and Zhengxin Zeng and Ruiheng Chang and Mingzheng Li and Hao Sun and Weiwei Deng and Feng Sun and Qi Zhang},
booktitle = {EMNLP 2025},
year = {2025}
}