- ホーム
- > 洋書
- > 英文書
- > Computer / General
Full Description
This book constitutes the proceedings of the 10th China Conference on Knowledge Graph and Semantic Computing, CCKS 2025, held in Fuzhou, China, during September 19-21, 2025.
The 22 full papers presented in this book were carefully reviewed and selected from 112 submissions. They were organized into the following topical sections: Knowledge Graph Construction and Integration; Large Models Enhanced by Knowledge Graphs; Applications of Knowledge Graphs and Large Models/Agents; Open Resources for Knowledge Graphs and Large Models; Evaluations.
Contents
.- Knowledge Graph Construction and Integration.
.- A Cross-Subgraph Attention Fusion and Comparison Method for Contrastive Learning Based Knowledge Graph Completion.
.- A Preliminary Attempt to Generate a Sichuan Dialect Handbook by LLMs.
.- EDREL: Document-level Relation Extraction with Evidence and Logical Rules.
.- Knowledge Retrieval-Augmented Interest learning for Recommendation.
.- Large Models Enhanced by Knowledge Graphs.
.- Multi-granularity Hierarchical RAG for Welding Parameter Recommendation.
.- Lag-Relative Sparse Attention In Long Context Training.
.- VIKA: Vectorized Indispensable Knowledge-subgraph Augmentation for Large Language Models.
.- Traff-LLM: A Spatio-Temporal Knowledge-Guided Large Language Model for Traffic Flow Prediction.
.- Applications of Knowledge Graphs and Large Models/Agents.
.- MAEPS: Multi-Agent Event Prediction System Based on Human Expert Team Collaboration Simulation.
.- Zero-shot Instruction Generation via Dual-Alignment Instruction Wrappers with Summary-Text fused instruction wrappers.
.- FEFT: A Feedback-enhanced Evaluation Fine-tuning Framework for Financial Report Summarization.
.- Iterative Generation Method for Factual QA in Large Language Models Based on Semantic Entropy Verification.
.- Open Resources for Knowledge Graphs and Large Models.
.- Autism Children Education Knowledge Graph: Construction and Validation.
.- C-Voice: Culturally-grounded Multi-dimensional Alignment of LLMs with Chinese Social Values.
.- Evaluations.
.- HiParse-RAG: A High-Fidelity Document Parsing and Hybrid Retrieval Multi-Model Fusion Framework for Complex Academic Question Answering.
.- HybriDoc: An Adaptive Multi-Path Framework for End-to-End Document Structure Extraction.
.- Pre-training for Document Structure Extraction with Lightweight Model Architecture.
.- Robust Detection of AI-Generated Text: Insights on Evolving LLMs and Adversarial Data.
.- A Fact-Aware Cascaded Framework for Dynamic-granularity Timeline Summarization.
.- Multi-Agent for Dynamic-Granularity Timeline Summarization.
.- Advancing Grounded Multimodal NER via Self-Reflective Prompt Refinement and Visual Noise Mitigation.
.- ReFineG: Synergizing Small Supervised Models and LLMs for Low-Resource Grounded Multimodal NER.



