About
Welcome! I am Pengyang Shao (邵鹏阳), currently a visiting postdoctoral researcher at NExT++ Lab, National University of Singapore, mentored by Prof. Tat-Seng Chua. I received my Ph.D. in July 2025 from Hefei University of Technology, under the supervision of Prof. Meng Wang. My current research focuses on Trustworthy AI, particularly LLM unlearning and safety, as well as latent knowledge in large language models.
I have also mentored students in related research directions. For example, I supervised Naixin Zhai, who published at ACL 2026 Main Conference as the first author, and Jilong Liu, who published at AAAI 2026. If you are interested in my research, feel free to reach out for discussion.
Outside of work, I enjoy playing badminton and running.
Featured Publications
BalDRO: A Distributionally Robust Optimization based Framework for LLM Unlearning. WWW 2026. [pdf] [code]
We propose BalDRO, a distributionally robust optimization framework that addresses sample-wise imbalance in LLM unlearning. By formulating unlearning as a min–sup optimization, BalDRO adaptively emphasizes hard-to-forget samples and prevents over-forgetting of easy ones.
We propose BalDRO, a distributionally robust optimization framework that addresses sample-wise imbalance in LLM unlearning. By formulating unlearning as a min–sup optimization, BalDRO adaptively emphasizes hard-to-forget samples and prevents over-forgetting of easy ones.
Exploring Heterogeneity and Uncertainty for Graph-based Cognitive Diagnosis Models in Intelligent Education. KDD 2025. [pdf] [code]
ISG-CD addresses two key challenges in GNN-based cognitive diagnosis: interaction heterogeneity and uncertainty in edge semantics. It introduces a semantic-aware graph model with an information-bottleneck-based edge differentiation mechanism to suppress noisy interactions during message passing.
ISG-CD addresses two key challenges in GNN-based cognitive diagnosis: interaction heterogeneity and uncertainty in edge semantics. It introduces a semantic-aware graph model with an information-bottleneck-based edge differentiation mechanism to suppress noisy interactions during message passing.
Publications
* denotes corresponding author. † denotes equal contribution.
Preprints
- Enyi Shi†, Pengyang Shao†, Yanxin Zhang, Chenhang Cui, Jiayi Lyu, Xu Xie, Xiaobo Xia, Fei Shen*, Tat-Seng Chua. Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models. [pdf]
Published / Accepted
- Naixin Zhai, Pengyang Shao*, Binbin Zheng, Yonghui Yang, Fei Shen, Long Bai, Xun Yang*. Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning. ACL 2026, main conference, just accepted. [pdf]
- Pengyang Shao, Le Wu, Kun Zhang, Lei Chen, Meng Wang. Privacy Matters: Data Attack to Make User Preferences Unlearnable in Recommendation. ACM TOIS 2026. [pdf]
- Pengyang Shao, Naixin Zhai, Lei Chen, Yonghui Yang, Fengbin Zhu*, Xun Yang*, Meng Wang. BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning. WWW 2026. [pdf]
- Pengyang Shao, Lei Chen*, Fei Liu, Yonghui Yang, Xun Yang, Meng Wang*. Multi-Agent Debate based Concept Augmentation for Enhanced Cognitive Diagnosis. KDD 2026 August Cycle. [pdf]
- Jilong Liu, Pengyang Shao*, Wei Qin, Fei Liu, Yonghui Yang, Richang Hong*. Debate over Mixed-knowledge: A Robust Multi-Agent Framework for Incomplete Knowledge Graph Question Answering. AAAI 2026. [pdf]
- Pengyang Shao†, Yonghui Yang†, Chen Gao, Lei Chen, Kun Zhang, Chenyi Zhuang, Le Wu, Yong Li, Meng Wang*. Exploring Heterogeneity and Uncertainty for Graph-based Cognitive Diagnosis Models in Intelligent Education. KDD 2025. [pdf]
- Pengyang Shao, Le Wu*, Kun Zhang, Defu Lian, Richang Hong, Yong Li, Meng Wang*. Average User-side Counterfactual Fairness for Collaborative Filtering. ACM TOIS, 2024. [pdf]
- Pengyang Shao, Le Wu*, Lei Chen, Kun Zhang, Meng Wang*. FairCF: Fairness-aware collaborative filtering. Science China Information Sciences, 2022. [pdf]
- Pengyang Shao, Zihan Wang, Junsong Xie, Yonghui Yang, Meng Wang. Towards Reliable Cross-Domain Recommendation: A Disentangled Global Graph Learning based Framework. Frontiers of Computer Science, 2025. [pdf]
- Pengyang Shao, Kun Zhang*, Chen Gao*, Lei Chen, Miaomiao Cai, Le Wu, Yong Li, Meng Wang. Breaking student-concept sparsity barrier for cognitive diagnosis. Frontiers of Computer Science, 2025. [pdf]
Academic Services
- Journal/Conference Reviewer: IEEE TKDE, ACM ToRS/TOIS, IJCAI, KDD, WWW, AAAI, ACL etc.
Awards
- China Association for Science and Technology (CAST) Young Talent Support Program (PhD Special Track) 2024
- First-Class Graduate Academic Scholarship (awarded annually) 2021-2024
- Outstanding Graduate of Anhui Province 2019