CID-GraphRAG: Enhancing Multi-Turn Dialogue Systems through Dual-Pathway Retrieval of Conversation Flow and Context Semantics
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_ | 1866918328288673792 |
|---|---|
| author | Zhu, Ziqi Hu, Tao Zhang, Honglong Yang, Dan Chen, Hangeng Zhang, Mengran Chen, Xilun |
| author_facet | Zhu, Ziqi Hu, Tao Zhang, Honglong Yang, Dan Chen, Hangeng Zhang, Mengran Chen, Xilun |
| contents | We present CID-GraphRAG (Conversational Intent-Driven Graph Retrieval-Augmented Generation), a novel framework that addresses the limitations of existing dialogue systems in maintaining both contextual coherence and goal-oriented progression in multi-turn customer service conversations. Unlike traditional RAG systems that rely solely on semantic similarity or static knowledge graphs, CID-GraphRAG constructs intent transition graphs from goal-achieved historical dialogues and implements a dual-retrieval mechanism that balances intent-based graph traversal with semantic search. This approach enables the system to simultaneously leverage both conversational intent flow patterns and contextual semantics, significantly improving retrieval quality and response quality. In extensive experiments on real-world customer service dialogues, we demonstrated that CID-GraphRAG significantly outperforms both semantic-based and intent-based baselines across automatic metrics, LLM-as-a-Judge evaluations and human evaluations, with relative gains of 11.4% in BLEU, 4.9% in ROUGE, and 5.9% in METEOR. Most notably, CID-GraphRAG achieves a 57.9% improvement in response quality according to LLM-as-a-Judge evaluations. These results demonstrate that integrating intent transition structures with semantic retrieval creates a synergistic effect that neither approach achieves independently, establishing CID-GraphRAG as an effective framework for real-world multi-turn dialogue systems in customer service and other knowledge-intensive domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19385 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CID-GraphRAG: Enhancing Multi-Turn Dialogue Systems through Dual-Pathway Retrieval of Conversation Flow and Context Semantics Zhu, Ziqi Hu, Tao Zhang, Honglong Yang, Dan Chen, Hangeng Zhang, Mengran Chen, Xilun Artificial Intelligence We present CID-GraphRAG (Conversational Intent-Driven Graph Retrieval-Augmented Generation), a novel framework that addresses the limitations of existing dialogue systems in maintaining both contextual coherence and goal-oriented progression in multi-turn customer service conversations. Unlike traditional RAG systems that rely solely on semantic similarity or static knowledge graphs, CID-GraphRAG constructs intent transition graphs from goal-achieved historical dialogues and implements a dual-retrieval mechanism that balances intent-based graph traversal with semantic search. This approach enables the system to simultaneously leverage both conversational intent flow patterns and contextual semantics, significantly improving retrieval quality and response quality. In extensive experiments on real-world customer service dialogues, we demonstrated that CID-GraphRAG significantly outperforms both semantic-based and intent-based baselines across automatic metrics, LLM-as-a-Judge evaluations and human evaluations, with relative gains of 11.4% in BLEU, 4.9% in ROUGE, and 5.9% in METEOR. Most notably, CID-GraphRAG achieves a 57.9% improvement in response quality according to LLM-as-a-Judge evaluations. These results demonstrate that integrating intent transition structures with semantic retrieval creates a synergistic effect that neither approach achieves independently, establishing CID-GraphRAG as an effective framework for real-world multi-turn dialogue systems in customer service and other knowledge-intensive domains. |
| title | CID-GraphRAG: Enhancing Multi-Turn Dialogue Systems through Dual-Pathway Retrieval of Conversation Flow and Context Semantics |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2506.19385 |