About
I am a Research Fellow at Duke-NUS Medical School & NUS CQT (advised by Prof. Enrico Petretto) and Nanyang Technological University (advised by Prof. Erik Cambria).
My research focuses on Large Language Model Reasoning, Knowledge Graph Question Answering, and their applications in Quantum Computing and AI-driven Drug Design. I am particularly interested in developing faithful reasoning methods that enhance the interpretability and reliability of AI systems.
I have published multiple first-author papers at top venues including AAAI, SIGIR, COLING, and journals such as Information Fusion (IF=15.5).
Selected Publications
View All →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)
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)
A flow-guided DPO method for knowledge graph reasoning using tree structures, published at SIGIR 2025.
News
Our paper LLMdoctor has been accepted by AAAI 2026!
Received the National Scholarship for Doctoral Students (2025).
Our paper on Flow-guided DPO has been accepted by SIGIR 2025!
Paper accepted by Information Fusion (IF=15.5).
Two papers accepted by COLING 2025 and ICASSP 2025.