MME-RAG: Multi-Manager-Expert Retrieval-Augmented Generation for Fine-Grained Entity Recognition in Task-Oriented Dialogues
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918203323580416 |
|---|---|
| author | Xue, Liang Liu, Haoyu Tian, Yajun Zhong, Xinyu Liu, Yang |
| author_facet | Xue, Liang Liu, Haoyu Tian, Yajun Zhong, Xinyu Liu, Yang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_12213 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MME-RAG: Multi-Manager-Expert Retrieval-Augmented Generation for Fine-Grained Entity Recognition in Task-Oriented Dialogues Xue, Liang Liu, Haoyu Tian, Yajun Zhong, Xinyu Liu, Yang Computation and Language Artificial Intelligence 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. |
| title | MME-RAG: Multi-Manager-Expert Retrieval-Augmented Generation for Fine-Grained Entity Recognition in Task-Oriented Dialogues |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2511.12213 |