Publications
A collection of my research work.
LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models
Tiesunlong Shen, others
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2026
A novel token-level flow-guided preference optimization method for efficient test-time alignment of LLMs.
Flow-guided Direct Preference Optimization for Knowledge Graph Reasoning with Trees
Tiesunlong Shen, Rui Mao, Jin Wang, others
Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2025
A flow-guided DPO method for knowledge graph reasoning using tree structures, published at SIGIR 2025.
Insight at the Right Spot: Provide Decisive Subgraph Information to Graph LLM with Reinforcement Learning
Tiesunlong Shen, Erik Cambria, Jin Wang, others
Information Fusion 2025
A reinforcement learning approach to enhance Graph LLM reasoning with decisive subgraph information. Published in Information Fusion (IF=15.5).
Reasoning with Trees: Faithful Question Answering over Knowledge Graph
Tiesunlong Shen, Jin Wang, Xuejie Zhang, others
Proceedings of the 31st International Conference on Computational Linguistics (COLING) 2025
A tree-based framework for faithful knowledge graph question answering, published at COLING 2025.
Knowledge Distillation via Adaptive Meta-Learning for Graph Neural Network
Tiesunlong Shen, Jin Wang, Xuejie Zhang
Information Sciences 2025
An adaptive meta-learning method for GNN knowledge distillation, published in Information Sciences (IF=8.1).
Hop-level Direct Preference Optimization for Knowledge Graph Reasoning with Trees
Tiesunlong Shen, Jin Wang, Xuejie Zhang, others
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025
A hop-level DPO method for tree-based knowledge graph reasoning, published at ICASSP 2025.
Graphs get Personal: Learning Representation with Contextual Pretraining for Collaborative Filtering
Tiesunlong Shen, You Zhang, Jin Wang, others
Applied Intelligence 2023
A contextual pretraining method for graph-based collaborative filtering, published in Applied Intelligence (IF=5.3).