Conversational Intent-Driven GraphRAG: Enhancing Multi-Turn Dialogue Systems through Adaptive Dual-Retrieval of Flow Patterns and Context Semantics

2025-06-24

AI Summary

To address the challenge of jointly preserving contextual coherence and goal-directedness in multi-turn customer service dialogues, this paper proposes CID-GraphRAG: a novel framework that models dialogue history as a dynamic intent transition graph and introduces an adaptive dual-channel retrieval mechanism. This mechanism synergistically enables intent-driven graph traversal and semantics-aware contextual retrieval. By integrating structured intent flow into the RAG paradigm, CID-GraphRAG overcomes the limitations of conventional single-channel semantic retrieval. Evaluated via LLM-as-judge on real-world customer service data, it significantly improves response quality—achieving +11% BLEU, +5% ROUGE-L, +6% METEOR, and a 58% gain in LLM-assessed response quality. The core contribution lies in establishing a new graph-augmented RAG paradigm that jointly models intent and semantics.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Conversational AI/Dialog Systems
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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 (Conversation RAG) or standard knowledge graphs (GraphRAG), CID-GraphRAG constructs dynamic intent transition graphs from goal achieved historical dialogues and implements a dual-retrieval mechanism that adaptively balances intent-based graph traversal with semantic search. This approach enables the system to simultaneously leverage both conversional intent flow patterns and contextual semantics, significantly improving retrieval quality and response quality. In extensive experiments on real-world customer service dialogues, we employ both automatic metrics and LLM-as-judge assessments, demonstrating that CID-GraphRAG significantly outperforms both semantic-based Conversation RAG and intent-based GraphRAG baselines across all evaluation criteria. Quantitatively, CID-GraphRAG demonstrates substantial improvements over Conversation RAG across automatic metrics, with relative gains of 11% in BLEU, 5% in ROUGE-L, 6% in METEOR, and most notably, a 58% improvement in response quality according to LLM-as-judge evaluations. These results demonstrate that the integration of intent transition structures with semantic retrieval creates a synergistic effect that neither approach achieves independently, establishing CID-GraphRAG as an effective framework for addressing the challenges of maintaining contextual coherence and goal-oriented progression in knowledge-intensive multi-turn dialogues.

Problem

• Enhancing multi-turn dialogue systems with adaptive dual-retrieval
• Balancing intent-based graph traversal and semantic search
• Improving contextual coherence and goal-oriented progression

Innovation

• Dynamic intent transition graphs construction
• Dual-retrieval mechanism balancing intent and semantics
• Synergistic integration of intent and semantic retrieval