MME-RAG：面向任务型对话细粒度实体识别的多管理者-专家检索增强生成框架
MME-RAG: Multi-Manager-Expert Retrieval-Augmented Generation for Fine-Grained Entity Recognition in Task-Oriented Dialogues
AI总结：
针对任务型对话细粒度实体识别中LLM的领域适配与检索可控性难题，提出MME-RAG多管理者-专家检索增强生成框架，经多数据集验证性能优于基线，具备良好鲁棒性与跨域泛化性。
摘要：
细粒度实体识别对任务型对话中的推理与决策至关重要，但当前大语言模型（LLM）仍面临领域适配与检索可控性方面的挑战。本文提出MME-RAG，即多管理者-专家检索增强生成框架，将实体识别拆解为两个协同阶段：由轻量级管理者完成类型层面判断，由专门化专家完成跨度层面抽取。每个专家配有KeyInfo检索器，可在推理阶段注入语义对齐的少样本示例，无需额外训练即可实现精准、适配领域的抽取。在CrossNER、MIT-Movie、MIT-Restaurant以及本文新构建的多领域客服数据集上的实验表明，MME-RAG在多数领域的表现优于近期基线模型。消融实验进一步证明，层级拆解与KeyInfo引导检索是鲁棒性和跨域泛化能力的核心驱动因素，使MME-RAG成为自适应对话理解领域可扩展、可解释的解决方案。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
