Congratulations to Dr. Depeng Xu on a Major Research Achievement!

We are proud to share that Dr. Depeng Xu’s paper, “Fine-tuning LLMs with Cross-Attention-based Weight Decay for Bias Mitigation,” has been accepted at EMNLP 2025, one of the top-tier international conferences in natural language processing.

This outstanding research contributes to advancing fairness and trustworthiness in large language models, aligning closely with the mission of the Center for Trustworthy Artificial Intelligence through Model Risk Management (TAIMing AI) at UNC Charlotte.

Dr. Xu’s project also received a 2025 TAIMing AI Seed Grant Award, which provided crucial support for the development of this work. The Center congratulates Dr. Xu and the research team on this accomplishment and looks forward to the continued impact of their research on AI innovation and responsible development.