报告题目：Exploring Trustworthy Foundation Models: Benchmarking, Finetuning and Reasoning

报告时间：2025年6月26日下午3点

报告地点：3044am永利集团B404会议室

报告人：Bo Han

报告人单位：香港浸会大学

报告人简介：Bo Han is an Assistant Professor in Machine Learning at Hong Kong Baptist University, and a BAIHO Visiting Scientist at RIKEN AIP. He was a Visiting Research Scholar at MBZUAI MLD, a Visiting Faculty Researcher at Microsoft Research and Alibaba DAMO Academy, and a Postdoc Fellow at RIKEN AIP. He received his Ph.D. degree in Computer Science from University of Technology Sydney. He has served as Senior Area Chair of NeurIPS, and Area Chairs of NeurIPS, ICML and ICLR. He has also served as Associate Editors of IEEE TPAMI, MLJ and JAIR, and Editorial Board Members of JMLR and MLJ. He received Outstanding Paper Award at NeurIPS, Most Influential Paper at NeurIPS, and Outstanding Student Paper Award at NeurIPS Workshop.

报告摘要：In the current landscape of machine learning, where foundation models must navigate imperfect real-world conditions such as noisy data and unexpected inputs, ensuring their trustworthiness through rigorous benchmarking, safety-focused finetuning, and robust reasoning is more critical than ever. In this talk, I will focus on three recent research advancements that collectively advance these dimensions, offering a comprehensive approach to building trustworthy foundation models. For benchmarking, I will introduce CounterAnimal, a dataset designed to systematically evaluate CLIP’s vulnerability to realistic spurious correlations, revealing that scaling models or data quality can mitigate these biases, yet scaling data alone does not effectively address them. Transitioning to finetuning, we delve deep into the process of unlearning undesirable model behaviors. We propose a general framework to examine and understand the limitations of current unlearning methods and suggest enhanced revisions for more effective unlearning. Furthermore, addressing reasoning, we investigate the reasoning robustness under noisy rationales by constructing the NoRa dataset and propose contrastive denoising with noisy chain-of-thought, a method that markedly improves denoising-reasoning capabilities by contrasting noisy inputs with minimal clean supervision. Furthermore, l will introduce the newly established Trustworthy Machine Learning and Reasoning (TMLR) Group at Hong Kong Baptist University.

邀请人：杜博、王增茂