Kangzheng Liu — accepted AI-conference papers

2025

LGA: LLM-GNN Aggregation for Temporal Evolution Attribute Graph Prediction

Feng Zhao, Ruoyu Chai, Kangzheng Liu, Xianggan Liu

EMNLP 2025

Temporal evolution attribute graph prediction, a key task in graph machine learning, aims to forecast the dynamic evolution of node attributes over time. While recent advances in Large Language Models (LLMs) have enabled their use in enhancing node representations for integration with Graph Neural N

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Priority on High-Quality: Selecting Instruction Data via Consistency Verification of Noise Injection

Hong Zhang, Feng Zhao, Ruilin Zhao, Cheng Yan, Kangzheng Liu

EMNLP 2025

Large Language Models (LLMs) have demonstrated a remarkable understanding of language nuances through instruction tuning, enabling them to effectively tackle various natural language processing tasks. Recent research has focused on the quality of instruction data rather than the quantity of instruct

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗