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