Publications

CARE: A Disagreement Detection Framework with Concept Alignment and Reasoning Enhancement
Jiyuan Liu, Jielin Song, Yunhe Pang, Yanghui Rao†
-- Explore the Conceptual Understanding and Reasoning Capabilities of LLMs on Social Media!
EMNLP, 2025    [Paper] [Code]

Neural Topic Modeling via Contextual and Graph Information Fusion
Jiyuan Liu, Jiaxing Yan, Chunjiang Zhu, Xingyu Liu, Qing Li, Yanghui Rao†
-- Combining graphs and contextual information can lead to better topic modeling.
EMNLP, 2025    [Paper] [Code]

GeM: Gaussian Embeddings with Multi-hop Graph Transfer for Next POI Recommendation
Wenqian Mu,∗, Jiyuan Liu*, Yongshun Gong†, Ji Zhong, Wei Liu, Haoliang Sun, Xiushan Nie, Yilong Yin, Yu Zheng
-- Combining the static transition graph of Points of Interest (POI) with dynamic Gaussian embeddings can enable more precise POI recommendations.
Neural Network, 2025    [Paper] [Code]

Unsupervised Hierarchical Topic Modeling via Anchor Word Clustering and Path Guidance
Jiyuan Liu*, Jiyuan Liu, Hegang Chen, Chunjiang Zhu, Yanghui Rao†
-- Anchors can facilitate hierarchical topic modeling.
EMNLP findings, 2024    [Paper] [Code]