Research & Projects
Research & Projects
Images Speak Louder than Words: Understanding and Mitigating Bias in Vision-Language Model from a Causal Mediation Perspective
Zhaotian Weng, Zijun Gao, Jerone Andrews, Jieyu Zhao. EMNLP 2024.
BIASINSPECTOR: Detecting Bias in Structured Data through LLM Agents
Haoxuan Li, Mingyu Derek Ma, Jen-tse Huang, Zhaotian Weng, Wei Wang, Jieyu Zhao. Arxiv preprint.
Online Open-set Semi-supervised Object Detection with Dual Competing Head
Zerun Wang, Ling Xiao, Liuyu Xiang, Zhaotian Weng, Toshihiko Yamasaki. Arxiv preprint.
LLM Self-contradictory Hallucination Mitigation via Retrieval-Based Post-Processing
Zhaotian Weng, Xingjian Dong, Liyan Huang, Jingwen Qi. SoCal NLP Symposium 2024.
What’s Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning
Zhaotian Weng, Haoxuan Li, Jieyu Zhao, Kuan-Hao Huang. under review
Evaluating and Improving Context-aware Privacy Protection in Vison-Language Models
Zhaotian Weng, Haoxuan Li, Jieyu Zhao. in preparation