Mind the Gap: A Dual Knowledge Graph Framework for Unified Multi-task User Intent Inference
Summary
This paper proposes DKG-MTI, a dual knowledge graph framework that augments LLM-based inference with structure-aware knowledge alignment to jointly predict aspect ratings and generate user intent statements from online travel reviews.
View Cached Full Text
Cached at: 08/10/26, 07:59 AM
# Mind the Gap: A Dual Knowledge Graph Framework for Unified Multi-task User Intent Inference Source: [https://arxiv.org/abs/2608.06752](https://arxiv.org/abs/2608.06752) [View PDF](https://arxiv.org/pdf/2608.06752) > Abstract:This paper proposes DKG\-MTI, a dual knowledge graph framework for unified multi\-task user intent inference from online travel reviews\. Existing approaches often rely on hierarchical pipelines that suffer from error propagation or retrieval methods that ignore structural relationships in domain knowledge\. To address these limitations, we introduce an inference\-only knowledge augmentation framework that dynamically constructs a User\-Specific Intent Knowledge Graph from each review and aligns it with a Global Hotel Knowledge Graph through structure\-aware semantic smoothing\. The aligned knowledge is combined with the original review and processed by a large language model to simultaneously predict aspect ratings and generate reverse user intent statements\. Experiments on TripAdvisor reviews show that DKG\-MTI consistently outperforms strong LLM and retrieval\-based baselines in both classification and intent generation tasks, demonstrating the effectiveness of structure\-aware knowledge alignment for scalable and explainable intent inference\. ## Submission history From: Chih Hao Ku \[[view email](https://arxiv.org/show-email/c15464c5/2608.06752)\] **\[v1\]**Fri, 7 Aug 2026 03:18:13 UTC \(1,205 KB\)
Similar Articles
MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion
Proposes M2GDT, a novel MKGC framework that uses an MLLM-guided diffusion transformer with relation-adaptive mixture-of-experts to align and denoise multimodal features, outperforming baselines on three benchmark datasets.
Dual-Path LLM Reasoning for Multimodal Few-Shot Knowledge Graph Completion
Proposes DuPLeR, a dual-path LLM reasoning framework for multimodal few-shot knowledge graph completion, combining LLM-derived type priors with factual structures to improve inductive KGC under data scarcity.
Travel-Oriented Reasoning Large Language Model via Domain-Specific Knowledge Graphs
This paper proposes a modular pipeline that uses a domain-specific knowledge graph to generate multi-hop QA pairs and fine-tune a reasoning LLM (Qwen3-4B) for the travel domain, achieving 82.4% exact match accuracy, significantly outperforming the baseline.
Conditional Diffusion Guided Knowledge Transfer for Multi-Domain Knowledge Graph Completion
Proposes a conditional diffusion-guided knowledge transfer framework for multi-domain knowledge graph completion, generating domain-general entity embeddings without suppressing domain-specific information, achieving 4.3% average MRR improvement over state-of-the-art methods.
Incorporating Cognitive Load and Knowledge Transfer for Multi-Domain Knowledge Tracing
This paper proposes LT-MKT, a method for multi-domain knowledge tracing that incorporates cognitive load and knowledge transfer using large language models to construct a hierarchical graph, achieving state-of-the-art performance on real-world datasets.