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.
@article{arxiv.2409.20434,
title = {QAEncoder: Towards Aligned Representation Learning in Question Answering Systems},
author = {Zhengren Wang and Qinhan Yu and Shida Wei and Zhiyu Li and Feiyu Xiong and Xiaoxing Wang and Simin Niu and Hao Liang and Wentao Zhang},
journal= {arXiv preprint arXiv:2409.20434},
year = {2025}
}