QAEncoder: Towards Aligned Representation Learning in Question Answering Systems
Zhengren Wang, Qinhan Yu, Shida Wei, Zhiyu Li, Feiyu Xiong, Xiaoxing Wang, Simin Niu, Hao Liang
Abstract
Modern QA systems entail retrieval-augmented generation (RAG) for accurate and trustworthy responses. However, the inherent gap between user queries and relevant documents hinders precise matching. We introduce QAEncoder, a training-free approach to bridge this gap. Specifically, QAEncoder estimates the expectation of potential queries in the embedding space as a robust surrogate for the document embedding, and attaches document fingerprints to effectively distinguish these embeddings. Extensive experiments across diverse datasets, languages, and embedding models confirmed QAEncoder’s alignment capability, which offers a simple-yet-effective solution with zero additional index storage, retrieval latency, training costs, or catastrophic forgetting and hallucination issues. The repository is publicly available at https://github.com/IAAR-Shanghai/QAEncoder.
BibTeX
@inproceedings{wang-etal-2025-qaencoder,
title = "{QAE}ncoder: Towards Aligned Representation Learning in Question Answering Systems",
author = "Wang, Zhengren and
Yu, Qinhan and
Wei, Shida and
Li, Zhiyu and
Xiong, Feiyu and
Wang, Xiaoxing and
Niu, Simin and
Liang, Hao and
Zhang, Wentao",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.217/",
doi = "10.18653/v1/2025.acl-long.217",
pages = "4306--4332",
ISBN = "979-8-89176-251-0"
}