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

• URL: http://arxiv.org/abs/2506.19385v1
• Date: Tue, 24 Jun 2025 07:20:45 GMT
• Title: Conversational Intent-Driven GraphRAG: Enhancing Multi-Turn Dialogue Systems through Adaptive Dual-Retrieval of Flow Patterns and Context Semantics
• Abstract summary: CID-GraphRAG (Conversational Intent-Driven Graph Retrieval Augmented Generation)<n>We present a novel framework that addresses the limitations of existing dialogue systems in maintaining contextual coherence and goal-oriented progression in multi-turn customer service conversations.<n> CID-GraphRAG constructs dynamic intent transition graphs from goal achieved historical dialogues and implements a dual-retrieval mechanism that adaptively balances intent-based graph with semantic search.
• Score: 8.532295745134459
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Rethinking Message Passing as Retrieval for Text-Attributed Graph Learning [63.602658976990874]
  Graph neural networks (GNNs) are typically conceptualized as message-passing neural networks.<n>We present a retrieval-augmented view of GNNs: each layer makes predictions by applying anvariant to a node representation together with a permutation-in summary of retrieved graph context.<n>Motivated by this perspective, we propose RTA, a simple aggregation-based framework that replaces structural message passing with label-aware retrieval and propagation.
  arXiv  Detail & Related papers  (2026-08-27T07:25:44Z)
• TA-RAG: Tone Awareness as a Design Imperative for Retrieval-Augmented Generation [2.0304958287672448]
  Tone-Aware RAG (TA-RAG) is a conceptual architectural framework that positions communicative alignment alongside factual accuracy as a core design objective.<n>TA-RAG operationalises four constraints-stigma-free language, readability alignment, recipient-sensitive adaptation, and empathetic framing-across the retrieval, context construction, generation, and constraint validation phases.
  arXiv  Detail & Related papers  (2026-08-07T00:37:16Z)
• SKG-Eval: Stateful Evaluation of Multi-Turn Dialogue via Incremental Semantic Knowledge Graphs [0.0]
  SKG-Eval is a quasi-deterministic and interpretable framework that models dialogue as an evolving Semantic Knowledge Graph.<n>We show that SKG-Eval achieves higher correlation with human judgments and substantially improves detection of long-range inconsistencies in extended conversations.
  arXiv  Detail & Related papers  (2026-05-15T21:39:48Z)
• Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition [52.63676763985825]
  We propose a semantic-aware evaluation metric to assess recognition quality beyond token-level accuracy.<n>We design an agent framework to simulate human-like multi-turn interaction, enabling iterative refinement of recognition outputs.<n>We will release the code to facilitate future research in interactive and agentic ASR.
  arXiv  Detail & Related papers  (2026-04-10T09:02:42Z)
• RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation [0.7594105478663188]
  We introduce the RAG-DIVE, a Dynamic Interactive Validation and Evaluation approach.<n>RAG-DIVE simulates user interactions with RAG systems in multi-turn settings.<n>Our findings demonstrate that RAG-DIVE facilitates dynamic, interaction-driven evaluation for multi-turn conversations.
  arXiv  Detail & Related papers  (2026-01-30T15:32:14Z)
• Leveraging Spreading Activation for Improved Document Retrieval in Knowledge-Graph-Based RAG Systems [0.0]
  Retrieval-augmented generation (RAG) systems struggle to reliably retrieve and connect the multi-step evidence required for complicated reasoning tasks.<n>Most of the standard RAG frameworks regard all retrieved information as equally reliable, overlooking the varying credibility and interconnected nature of large textual corpora.<n>We propose a novel RAG framework that employs the spreading activation algorithm to retrieve information from a corpus of documents interconnected by automatically constructed knowledge graphs.
  arXiv  Detail & Related papers  (2025-12-17T19:38:35Z)
• D-SMART: Enhancing LLM Dialogue Consistency via Dynamic Structured Memory And Reasoning Tree [22.420810089099614]
  Large Language Models (LLMs) often exhibit factual inconsistencies and logical decay in extended, multi-turn dialogues.<n>We propose D--101, a model-agnostic framework designed to maintain multi-turn dialogue consistency.<n>We introduce new NLI-based metrics to better measure multiturn dialogue consistency.
  arXiv  Detail & Related papers  (2025-10-15T09:53:11Z)
• IAR2: Improving Autoregressive Visual Generation with Semantic-Detail Associated Token Prediction [77.06211178777939]
  IAR2 is an advanced autoregressive framework that enables a hierarchical semantic-detail synthesis process.<n>We show that IAR2 sets a new state-of-the-art for autoregressive image generation, achieving a FID of 1.50 on ImageNet.
  arXiv  Detail & Related papers  (2025-10-08T12:08:21Z)
• Knowledge-Graph Based RAG System Evaluation Framework [27.082302648704708]
  Large language models (LLMs) has become a significant research focus.<n>Retrieval Augmented Generation (RAG) greatly enhances generated content's reliability and relevance.<n> evaluating RAG systems remains a challenging task.
  arXiv  Detail & Related papers  (2025-10-02T20:36:21Z)
• Hybrid AI for Responsive Multi-Turn Online Conversations with Novel Dynamic Routing and Feedback Adaptation [2.4830284216463]
  This paper introduces a novel hybrid framework that integrates RAG with intent-based canned responses.<n>Our framework employs a dialogue context manager to ensure coherence in multi-turn interactions and incorporates a feedback loop to refine intents.<n> Experimental results demonstrate that the proposed framework achieves a balance of high accuracy (95%) and low latency (180ms)
  arXiv  Detail & Related papers  (2025-06-02T17:59:27Z)
• DO-RAG: A Domain-Specific QA Framework Using Knowledge Graph-Enhanced Retrieval-Augmented Generation [4.113142669523488]
  Domain-specific QA systems require generative fluency but high factual accuracy grounded in structured expert knowledge.<n>We propose DO-RAG, a scalable and customizable hybrid QA framework that integrates multi-level knowledge graph construction with semantic vector retrieval.
  arXiv  Detail & Related papers  (2025-05-17T06:40:17Z)
• ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation [8.223134723149753]
  We present an unsupervised framework that optimize Retrieval-Augmented Generation (RAG) systems.<n>By decomposing paragraphs into sentences, we dynamically re-weighting core content while preserving contextual coherence.<n>This framework has been validated across various datasets, Large Language Models (LLMs), and retrievers.
  arXiv  Detail & Related papers  (2025-02-12T07:32:48Z)
• Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs [0.8772713588571283]
  Chatty-Gen is a novel multi-stage retrieval-augmented generation platform for dialogue benchmarks.<n>Chatty-Gen decomposes the generation process into manageable stages and uses assertion rules for automatic validation.<n>Our experiments with several real and large KGs demonstrate that Chatty-Gen significantly outperforms state-of-the-art systems.
  arXiv  Detail & Related papers  (2025-01-17T02:48:29Z)
• CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation [68.81271028921647]
  We introduce CORAL, a benchmark designed to assess RAG systems in realistic multi-turn conversational settings. CORAL includes diverse information-seeking conversations automatically derived from Wikipedia. It supports three core tasks of conversational RAG: passage retrieval, response generation, and citation labeling.
  arXiv  Detail & Related papers  (2024-10-30T15:06:32Z)
• Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation [14.448198170932226]
  Think-on-Graph 2.0 (ToG-2) is a hybrid RAG framework that iteratively retrieves information from both unstructured and structured knowledge sources.<n>ToG-2 alternates between graph retrieval and context retrieval to search for in-depth clues relevant to the question.<n>It achieves overall state-of-the-art (SOTA) performance on 6 out of 7 knowledge-intensive datasets with GPT-3.5.
  arXiv  Detail & Related papers  (2024-07-15T15:20:40Z)
• Improved Contextual Recognition In Automatic Speech Recognition Systems By Semantic Lattice Rescoring [4.819085609772069]
  We propose a novel approach for enhancing contextual recognition within ASR systems via semantic lattice processing. Our solution consists of using Hidden Markov Models and Gaussian Mixture Models (HMM-GMM) along with Deep Neural Networks (DNN) models for better accuracy. We demonstrate the effectiveness of our proposed framework on the LibriSpeech dataset with empirical analyses.
  arXiv  Detail & Related papers  (2023-10-14T23:16:05Z)
• Dialogue Meaning Representation for Task-Oriented Dialogue Systems [51.91615150842267]
  We propose Dialogue Meaning Representation (DMR), a flexible and easily extendable representation for task-oriented dialogue. Our representation contains a set of nodes and edges with inheritance hierarchy to represent rich semantics for compositional semantics and task-specific concepts. We propose two evaluation tasks to evaluate different machine learning based dialogue models, and further propose a novel coreference resolution model GNNCoref for the graph-based coreference resolution task.
  arXiv  Detail & Related papers  (2022-04-23T04:17:55Z)
• DynaEval: Unifying Turn and Dialogue Level Evaluation [60.66883575106898]
  We propose DynaEval, a unified automatic evaluation framework. It is capable of performing turn-level evaluation, but also holistically considers the quality of the entire dialogue. Experiments show that DynaEval significantly outperforms the state-of-the-art dialogue coherence model.
  arXiv  Detail & Related papers  (2021-06-02T12:23:18Z)
• GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems [133.13117064357425]
  We propose a new evaluation metric GRADE, which stands for Graph-enhanced Representations for Automatic Dialogue Evaluation. Specifically, GRADE incorporates both coarse-grained utterance-level contextualized representations and fine-grained topic-level graph representations to evaluate dialogue coherence. Experimental results show that our GRADE significantly outperforms other state-of-the-art metrics on measuring diverse dialogue models.
  arXiv  Detail & Related papers  (2020-10-08T14:07:32Z)
• Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization [77.21951145754065]
  We propose a novel Cross- and Self-Modal Graph Attention Network (CSMGAN) that recasts this task as a process of iterative messages passing over a joint graph. Our CSMGAN is able to effectively capture high-order interactions between two modalities, thus enabling a further precise localization.
  arXiv  Detail & Related papers  (2020-08-04T08:25:24Z)
• Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System [49.39150449455407]
  HDNO is an option framework for designing latent dialogue acts to avoid designing specific dialogue act representations. We test HDNO on MultiWoz 2.0 and MultiWoz 2.1, the datasets on multi-domain dialogues, in comparison with word-level E2E model trained with RL, LaRL and HDSA.
  arXiv  Detail & Related papers  (2020-06-11T20:55:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.