Yulin Hu

Yulin Hu

SCIR, Harbin Institute of Technology

Yulin Hu 胡雨林

Hello, I am a master’s student at the Research Center for Social Computing and Information Retrieval (SCIR) at Harbin Institute of Technology (HIT), China. I am advised by Prof. Yanyan Zhao. My current research primarily focuses on the development and implementation of Socially-Responsible AI, with particular attention to its applications in:

  • Personalized & Emotional Dialogue Systems
  • Safety Alignment
  • Reasoning Enhancement
  • Multilingual Enhancement

Education

Main Publications

Personalized & Emotional Dialogue Systems

  • NeurIPS 2025 Weixiang Zhao*, Xingyu Sui*, Yulin Hu*, Jiahe Guo, Haixiao Liu, Biye Li, Yanyan Zhao, Bing Qin, Ting Liu. Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment. [paper]

  • EMNLP 2025 (Findings) Weixiang Zhao*, Xingyu Sui*, Xinyang Han, Yang Deng, Yulin Hu, Jiahe Guo, Libo Qin, Qianyun Du, Shijin Wang, Yanyan Zhao, Bing Qin, Ting Liu. Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter. [paper] [repo]

  • ACL 2024 (Main) Weixiang Zhao, Shilong Wang, Yulin Hu, Yanyan Zhao, Bing Qin, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che. SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models. ACL 2024 (Main). [paper] [repo]

  • ACL 2024 (Findings) Weixiang Zhao, Zhuojun Li, Shilong Wang, Yang Wang, Yulin Hu, Yanyan Zhao, Chen Wei, Bing Qin. Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence. ACL 2024 (Findings). [paper]

Safety Alignment

  • ACL 2025 (Main) Weixiang Zhao*, Yulin Hu*, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu. Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs. [paper] [repo]

  • 🏆 ACL 2025 (Main, 🌟Oral & Panel - Top 0.3% of Submissions) Weixiang Zhao, Yulin Hu, Yang Deng, Tongtong Wu, Wenxuan Zhang, Jiahe Guo, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu. MPO: Multilingual Safety Alignment via Reward Gap Optimization. [paper] [repo]

  • 🏆 EMNLP 2025 (Main, Oral) Weixiang Zhao*, Jiahe Guo*, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu. AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender. [paper] [repo]

  • arXiv:2405.13820 Weixiang Zhao, Yulin Hu, Zhuojun Li, Yang Deng, Jiahe Guo, Xingyu Sui, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu. Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching. [paper]

Reasoning Enhancement

  • arXiv:2503.17979 Weixiang Zhao*, Xingyu Sui*, Jiahe Guo*, Yulin Hu*, Yang Deng, Yanyan Zhao, Bing Qin, Wanxiang Che, Tat-Seng Chua, Ting Liu. Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities. [paper] [repo]

  • 🏆 NeurIPS 2025 (🌟Spotlight - Top 3.2% of Submissions) Weixiang Zhao, Jiahe Guo, Yang Deng, Tongtong Wu, Wenxuan Zhang, Yulin Hu, Xingyu Sui, Yanyan Zhao, Wanxiang Che, Bing Qin, Tat-Seng Chua, Ting Liu. When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners. [paper]

  • arXiv:2506.15647 Weixiang Zhao, Jiahe Guo, Yang Deng, Xingyu Sui, Yulin Hu, Yanyan Zhao, Wanxiang Che, Bing Qin, Tat-Seng Chua, Ting Liu. Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement. [paper]

Multilingual Enhancement

  • 🏆 NeurIPS 2025 (🌟Spotlight - Top 3.2% of Submissions) Weixiang Zhao, Jiahe Guo, Yang Deng, Tongtong Wu, Wenxuan Zhang, Yulin Hu, Xingyu Sui, Yanyan Zhao, Wanxiang Che, Bing Qin, Tat-Seng Chua, Ting Liu. When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners. [paper]

  • 🏆 ACL 2025 (Main, 🌟Oral & Panel - Top 0.3% of Submissions) Weixiang Zhao, Yulin Hu, Yang Deng, Tongtong Wu, Wenxuan Zhang, Jiahe Guo, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu. MPO: Multilingual Safety Alignment via Reward Gap Optimization.

  • ACL 2025 (Findings) Weixiang Zhao, Yulin Hu, Jiahe Guo, Xingyu Sui, Tongtong Wu, Yang Deng, Yanyan Zhao, Bing Qin, Wanxiang Che, Ting Liu. Lens: Rethinking Multilingual Enhancement for Large Language Models. [paper] [repo]

Internships

  • Dec 2024 - April 2025. Research Intern. Du Xiaoman (Beijing) Science Technology Co., Ltd, Beijing, China. Supervisor: Dr. Biye Li.

Selected Awards and Honors

  • Excellent Thesis, Harbin Institute of Technology, 2025