Welcome to my personal website!

I am a first-year PhD student under Professor Jing Li’s supervision at KLC Lab of Harbin Institute of Technology (HIT) based on Shenzhen, China.

I have recently embarked on my research journey in the world of Natural Language Processing (NLP). Here is my research interest:

• From Inner Workings Towards Value Alignment; From Powerful Towards Useful.

I am grateful to my supervisor, Professor Jing Li, for his patient and insightful guidance, and, valuable and continuous encouragement from my application period until the present research work. If you are interested in our group, feel free to go through the lab website and contact my supervisor.

Besides, I would also like to thank Professor Chen Ling, Professor Wei Wang, Hongbin Na and Zimu Wang, for their pleasant collaboration in research and professional help during my application.

Degrees

• Ph.D. in Computer Science, Harbin Institute of Technology, 2029.06 (expected)
• M.S. in Data Science, The University of Sydney, 2025.07
  • GPA: 3.25/4.00
• B.A. in Economics, The University of Sydney, 2023.12
  • GPA: 3.85/4.00

Papers

(The asterisk * appearing after authors means equal contribution.)

• [EMNLP2025] [2025] Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement
  • Author: Haotan Guo*, Jianfei He*, Jiayuan Ma*, Hongbin Na, Zimu Wang, Haiyang Zhang, Qi Chen, Wei Wang, Zijing Shi, Tao Shen, Ling Chen
  • Area: Industry Track
  • Award: Poster
  • Abstract: PCR ToxiCN dataset was introduced to demonstrate a challenge on Chinese social media moderation from phonetic cloaking replacement (PCR) and to evaluate LLMs’ detection ability on this challenge.
• [CLPsych2025] [2025] From Posts to Timelines: Modeling Mental Health Dynamics from Social Media Timelines with Hybrid LLMs
  • Author: Zimu Wang*, Hongbin Na*, Rena Gao, Jiayuan Ma, Yining Hua, Ling Chen, Wei Wang
  • Area: Shared Task at NAACL2025
  • Award: Ranked 3rd in the Shared Task
  • Abstract: This work proposes a hybrid large language model framework to model individual mental health dynamics by first identifying adaptive and maladaptive evidence in social media posts, and then synthetically generating user well-being scores as well as post-level and timeline-level summaries.
• [COLING2025] [2024] Detecting Conversational Mental Manipulation with Intent-Aware Prompting
  • Author: Jiayuan Ma*, Hongbin Na*, Zimu Wang, Yining Hua, Yue Liu, Wei Wang, Ling Chen
  • Area: Short Paper
  • Award: Best Short Paper, Oral
  • Abstract: Based on Theory of Mind as motivation, a new approach, Intent-Aware Prompting (IAP), was introduced to detect mental manipulation in dialogues, which notably reduces false negatives and improving overall performance on detection.

Internships

• 2023.12 - 2024.02, ESG Research Intern
  • PwC China (Shanghai, China)
• 2023.06 - 2023.08, VC Research Intern
  • Shenzhen Capital Group Co. Ltd (Shanghai, China)
• 2022.09 - 2022.12, IBD Research Intern
  • China Securities Co. Ltd (Beijing, China)
• 2021.06 - 2021.07, Consulting Assistant Intern
  • Capgemini Consulting (China) Co. Ltd (Hangzhou, China)

Skills

• Computing
  • Python, R, STATA, MS Office
• Languages
  • Chinese (Native), English (Fluent), Spanish (B1), Japanese (N4)
• Certificates
  • ACCA (passed 5/13)