avatar

Shaoyang Xu (徐邵洋)

PhD Student
Singapore University of Technology and Design (SUTD)
shaoyang_xu (at) mymail.sutd.edu.sg


About

PhD at inclusive NLP (iNLP) Lab (github) @ SUTD, led by Prof. Wenxuan Zhang. Before, Master with Prof. Deyi Xiong; Undergraduate with Assoc. Prof. Feng Jiang and Prof. Peifeng Li.

Research focuses on linguistic and cultural diversity in Large Language Models.

News

Service

Reviewer: ICLR-26, ACL-26, C3NLP-26, NeurIPS-26, EMNLP-26, AAAI-27

Research


(* indicates corresponding authors)

  1. Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack
    Long P. Hoang, Hai V. Le, Shaoyang Xu, Wei Lu, Wenxuan Zhang*
    pre-print-26
    PDF Code

  2. Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems
    Shaoyang Xu, Jingshen Zhang, Long P Hoang, Jinyuan Li, Wenxuan Zhang*
    pre-print-26
    PDF Code

  3. Process Rewards with Learned Reliability
    Jinyuan Li, Langlin Huang, Chengsong Huang, Shaoyang Xu, Donghong Cai, Yuyi Yang, Wenxuan Zhang, Jiaxin Huang*
    pre-print-26
    PDF Code

  4. MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook
    Yi Feng, Chen Huang, Zhibo Man, Ryner Tan, Long P. Hoang, Shaoyang Xu, Wenxuan Zhang*
    pre-print-26
    PDF Code

  5. Training Data Efficiency in Multimodal Process Reward Models
    Jinyuan Li, Chengsong Huang, Langlin Huang, Shaoyang Xu, Haolin Liu, Wenxuan Zhang, Jiaxin Huang*
    ICML 2026
    PDF Code

  6. Can Multi-agent Help Disambiguation in Multi-domain Translation?
    Zhibo Man, Shaoyang Xu, Yujie Zhang*, Yi Feng, Yuanmeng Chen, Yufeng Chen, Jinan Xu, Wenxuan Zhang*
    PDF Code

  7. Language of Thought Shapes Output Diversity in Large Language Models
    Shaoyang Xu, Wenxuan Zhang*
    ACL 2026
    PDF Code

  8. DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search
    Lei Yang, Shaoyang Xu, Jianxiang Peng, Shaolin Zhu, Deyi Xiong*
    EMNLP 2025
    PDF Code

  9. Self-Pluralising Culture Alignment for Large Language Models
    Shaoyang Xu, Yongqi Leng, Linhao Yu, Deyi Xiong*
    NAACL 2025
    PDF Code

  10. CONTRANS: Weak-to-Strong Alignment Engineering via Concept Transplantation
    Weilong Dong, Xinwei Wu, Renren Jin, Shaoyang Xu, Deyi Xiong*
    COLING 2025
    PDF Code

  11. FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data
    Haoran Sun, Renren Jin, Shaoyang Xu, Leiyu Pan, Menglong Cui, Jiangcun Dui, Yikun Lei, Lei Yang, Ling Shi, Juesi Xiao, Shaolin Zhu, Deyi Xiong*
    EMNLP 2024 Industry Track
    PDF Code

  12. Multilingual Large Language Models: A Systematic Survey
    Shaolin Zhu, Supryadi, Shaoyang Xu, Haoran Sun, Leiyu Pan, Menglong Cui, Jiangcun Du, Renren Jin, António Branco, Deyi Xiong*
    pre-print
    PDF Code

  13. Exploring Multilingual Human Value Concepts in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?
    Shaoyang Xu, Weilong Dong, Zishan Guo, Xinwei Wu, Deyi Xiong*
    EMNLP 2024 Findings
    PDF Code

  14. Mitigating Privacy Seesaw in Large Language Models: Augmented Privacy Neuron Editing via Activation Patching
    Xinwei Wu, Weilong Dong, Shaoyang Xu, Deyi Xiong*
    ACL 2024 Findings
    PDF Code

  15. Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?
    Shaoyang Xu, Junzhuo Li, Deyi Xiong*
    EMNLP 2023
    PDF

  16. Topic Segmentation via Discourse Structure Graph Network
    Shaoyang Xu, Feng Jiang, Peifeng Li*
    JOURNAL OF CHINESE INFORMATION PROCESSING, 2021.
    PDF Code


Powered by Jekyll and Minimal Light theme.