用动态信息流分析查询意图，提升跨域知识检索准确率
DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search
- 通过梯度与归因分析追踪模型内部意图路径
- 多原型对比学习实现跨源知识对齐，召回率提升5.38%
- 适合需要高精度跨域检索的生成任务应用
联邦检索（FR）通过调用多个外部知识源来缓解大语言模型在缺乏必要知识时的幻觉问题。然而，现有方法在处理模糊查询尤其是跨领域场景时，难以获取高质量相关文档，严重制约其下游生成性能。受动态信息流（DIF）启发，我们提出DFAMS框架，利用DIF识别隐含查询意图，并构建语义对齐的知识分区以实现异构源间精准检索。具体而言，DFAMS通过少量标注查询的梯度信号，结合基于Shapley值的归因分析，追踪与意图识别和子域边界检测相关的神经元激活路径。随后，利用DIF训练一个对齐模块，通过多原型对比学习实现细粒度源内建模与跨源语义对齐。在五个基准测试上的实验表明，相较于先进方法，DFAMS在知识分类准确率上最高提升14.37%，检索召回率提升5.38%，下游问答准确率提升6.45%，充分验证了其在复杂联邦检索场景中的有效性。代码已匿名公开于https://anonymous.4open.science/r/DFAMS/
原文摘要 · Abstract (English)
Federated Retrieval (FR) routes queries across multiple external knowledge sources, to mitigate hallucinations of LLMs, when necessary external knowledge is distributed. However, existing methods struggle to retrieve high-quality and relevant documents for ambiguous queries, especially in cross-domain scenarios, which significantly limits their effectiveness in supporting downstream generation tasks. Inspired by Dynamic Information Flow (DIF), we propose DFAMS, a novel framework that leverages DIF to identify latent query intents and construct semantically aligned knowledge partitions for accurate retrieval across heterogeneous sources. Specifically, DFAMS probes the DIF in LLMs by leveraging gradient signals from a few annotated queries and employing Shapley value-based attribution to trace neuron activation paths associated with intent recognition and subdomain boundary detection. Then, DFAMS leverages DIF to train an alignment module via multi-prototype contrastive learning, enabling fine-grained intra-source modeling and inter-source semantic alignment across knowledge bases. Experimental results across five benchmarks show that DFAMS outperforms advanced FR methods by up to 14.37\% in knowledge classification accuracy, 5.38\% in retrieval recall, and 6.45\% in downstream QA accuracy, demonstrating its effectiveness in complex FR scenarios. Our code are anonymous available at https://anonymous.4open.science/r/DFAMS/
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。