Yuan Wu

I am a pre-tenured associate professor at the School of Artificial Intelligence, Jilin University. My research interests include natural language processing, large language models, LLM evaluation, and LLM post-training.

I received my Bachelor degree from Beijing University of Chemical Technology, my Master degree from Lanzhou University, advised by Prof. Lian Li, and my Ph.D. from Carleton University, advised by Prof. Ahmed El-Roby and Prof. Diana Inkpen.

My group studies reliable, efficient, and trustworthy methods for building and evaluating large language models. I welcome inquiries from undergraduate and graduate students interested in natural language processing, LLM evaluation, post-training, domain adaptation, and trustworthy AI.

欢迎985高校本科生咨询保研、直博项目，有优惠政策。

Research Interests

• Large language model evaluation and benchmarking
• LLM post-training and parameter-efficient fine-tuning
• Trustworthy and reliable language models
• Domain adaptation and generalization for NLP
• Instruction following and model self-evaluation

Selected publications

1. BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models
   Yupeng Chang, Yi Chang, and Yuan Wu+
   In ICLR, 2026
   HTML · Code

2. SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling
   Yupeng Chang, Yuan Wu+, and Yi Chang
   In ACL, 2026
   HTML · Code

3. Rethinking Data Selection at Scale: Random Selection is Almost All You Need
   Tingyu Xia, Bowen Yu, Kai Dang, An Yang, Yuan Wu+, Yuan Tian, Yi Chang, and Junyang Lin
   In Findings of EMNLP, 2025
   HTML · Code

4. Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning
   Yue Zhou, Yuan Wu+, and Yi Chang
   In EMNLP, 2026
   HTML · Code

5. A Survey on Evaluation of Large Language Models
   Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu+, Linyi Yang, Kaijie Zhu, Hao Chen, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, Wei Ye, Yue Zhang, Yi Chang, Philip S. Yu, Qiang Yang, and Xing Xie
   ACM Transactions on Intelligent Systems and Technology, 2024
   DOI · Code

6. How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbations
   Yuxing Cheng, Yuan Wu+, and Yi Chang
   In EMNLP, 2026
   HTML · Code

News