通过分层专家机制提升对话中细粒度实体识别的准确性与适应性。
MME-RAG: Multi-Manager-Expert Retrieval-Augmented Generation for Fine-Grained Entity Recognition in Task-Oriented Dialogues
- 分两阶段处理：轻量级管理器判断类型，专家模型提取实体跨度。
- 引入关键信息检索器，推理时注入少量示例，无需再训练。
- 在多个数据集上表现优于基线，适合需要跨领域适应的对话系统。
细粒度实体识别对任务导向型对话中的推理与决策至关重要，但当前大语言模型在领域适配和检索可控性方面仍面临挑战。我们提出 MME-RAG 框架，将实体识别分解为两个协同阶段：由轻量级管理器完成类型判断，由专用专家执行跨度提取。每个专家配备一个 KeyInfo 检索器，在推理时注入语义对齐的少样本示例，实现精确且领域自适应的抽取，无需额外训练。在 CrossNER、MIT-Movie、MIT-Restaurant 以及我们新构建的多领域客服数据集上的实验表明，MME-RAG 在多数领域上优于近期基线。消融实验证明，层级分解与 KeyInfo 引导的检索是提升鲁棒性和跨域泛化能力的关键，确立了 MME-RAG 作为可扩展、可解释的自适应对话理解方案。
原文摘要 · Abstract (English)
Fine-grained entity recognition is crucial for reasoning and decision-making in task-oriented dialogues, yet current large language models (LLMs) continue to face challenges in domain adaptation and retrieval controllability. We introduce MME-RAG, a Multi-Manager-Expert Retrieval-Augmented Generation framework that decomposes entity recognition into two coordinated stages: type-level judgment by lightweight managers and span-level extraction by specialized experts. Each expert is supported by a KeyInfo retriever that injects semantically aligned, few-shot exemplars during inference, enabling precise and domain-adaptive extraction without additional training. Experiments on CrossNER, MIT-Movie, MIT-Restaurant, and our newly constructed multi-domain customer-service dataset demonstrate that MME-RAG performs better than recent baselines in most domains. Ablation studies further show that both the hierarchical decomposition and KeyInfo-guided retrieval are key drivers of robustness and cross-domain generalization, establishing MME-RAG as a scalable and interpretable solution for adaptive dialogue understanding.
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。