Hello! I’m Tiankai Yang, a first-year PhD student of Computer Science at the University of Southern California (USC), supervised by Prof. Yue Zhao. Prior, I earned a Master’s degree in Machine Learning and Data Science from USC and a Bachelor’s degree in Software Engineering from Nankai University, China.

My research focuses on anomaly detection, diversity in generation, synthetic generation, and trust & safety in large language models and agents.

News

• [10/2025] Our paper “AD-AGENT, a multi-agent LLM framework for anomaly detection” has been accepted to IJCNLP-AACL 2025 Findings! See our Preprint.
• [10/2025] We have a new paper on LLM routing; see our Preprint.
• [08/2025] We have two new papers accepted to EMNLP Findings 2025: one on causal methods for hallucination mitigation (Treble Counterfactual VLMs) and another introducing a benchmark for NLP anomaly detection (NLP-ADBench). See our Treble Preprint and NLP-ADBench Preprint!
• [05/2025] We have a new paper on benchmarking personalized conversational reasoning for LLMs (PersonaConvBench). See our Preprint!
• [05/2025] Our paper “AD-LLM: Benchmarking Large Language Models for Anomaly Detection” has been accepted to ACL 2025 Findings! See our Preprint.