用嵌入空间中的查询期望，让问答系统更精准匹配文档。
QAEncoder: Towards Aligned Representation Learning in Question Answering Systems
- 用查询期望替代文档嵌入，实现无训练对齐
- 零额外存储和推理延迟，兼容多种模型与语言
- 适合需要快速部署、避免幻觉的问答系统
现代问答系统依赖检索增强生成（RAG）以提供准确可信的回答。然而，用户查询与相关文档间的固有语义差距阻碍了精确匹配。本文提出QAEncoder，一种无需训练的方法来弥合这一差距。具体地，QAEncoder在嵌入空间中估计潜在查询的期望值，作为文档嵌入的鲁棒代理，并附加文档指纹以有效区分这些嵌入。在多个数据集、语言和嵌入模型上的广泛实验验证了QAEncoder的对齐能力，其提供了一种简单而有效的解决方案：零额外索引存储、检索延迟、训练成本，且无灾难性遗忘或幻觉问题。代码仓库已公开于 https://github.com/IAAR-Shanghai/QAEncoder。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。