About
I am a postdoctoral research fellow at the School of Computing, National University of Singapore (NUS), working with Prof. Anthony K. H. Tung, Prof. Wynne Hsu, and Prof. Mong Li Lee at the Centre for Trusted Internet and Community (CTIC).
My research focuses on trustworthy AI for open-world understanding and reasoning. I study how AI systems can reason reliably with incomplete, noisy, multimodal, or adversarial information, with applications in evidence retrieval, misinformation detection, question answering, and healthcare.
I received my B.Comp. in 2016 and Ph.D. in 2024 from NUS. My Ph.D., co-supervised by Prof. Anthony K. H. Tung and Prof. Hwee Tou Ng, focused on improving the robustness and evaluation of machine reading comprehension models.
Recent News
One paper was accepted to NeurIPS 2026 (spotlight).
Guest Lecturer CS2309 CS Research Methodology.
Won 1st Place in the Long-Form Analogy Evaluation Challenge.
Three papers were accepted to EMNLP 2026.
Invited Speaker at the NUS AI Institute x MSRA Summer School on Agentic AI.
Invited Lightning Talk Speaker at the Stanford x NUS CIVIC-AI Workshop.
Four papers were accepted to ACL 2026.
One paper was accepted to SIGMOD 2026.
Selected Publications
View All →Structure vs. Chaos: Asymmetric Entropic Optimization for Enforcing Instruction Hierarchy
Tianxiao Huang, Xinwei Liu, Zitong Shi, Yuxin Wu, Xuan Chen, Liangtao Zheng, Yixuan Tang*, Anthony Kum Hoe Tung
The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS)
Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection
Yixuan Tang, Yirui Zhang, Hang Feng, Anthony K. H. Tung
The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Reasoning Hijacking: The Fragility of Reasoning Alignment in Large Language Models
Yuansen Liu, Yixuan Tang*, Anthony K. H. Tung
The 64th Annual Meeting of the Association for Computational Linguistics (ACL)
SPARROW: Scalable Taxonomy Induction via Structure-Preserving Partitioning and Constraint-Guided Merging
Yirui Zhang, Yixuan Tang*, Yandong Sun, Mong-Li Lee, Anthony K. H. Tung
The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Asking the Right Questions: Ontology-Grounded Interpretable Embeddings for Biomedical Text
Yixuan Tang, Zhenghong Lin, Yandong Sun, Wynne Hsu, Mong-Li Lee, Anthony K. H. Tung
Findings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP)
The Missing Parts: Augmenting Fact Verification with Half Truth Detection
Yixuan Tang, Jincheng Wang, Anthony K. H. Tung
The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP)