Cheng Li

profile.JPG

I am an AI reseacher, working on human-centered AI.

I am a Master student at Institute of Software, Chinese Academy of Science. Previously, I was an undergraduate student at Tianjin University. In summer 2024, I had an internship at UIUC, advised by Prof.Heng Ji. Before that, I have a long internship at Microsoft Research Asia, advised by Prof.Xing Xie and Prof.Jindong Wang.

My research interests including:

  • AI for Social Science
  • Cultural Problem in Large Models
  • AI for Mental Health

news

May 26, 2025 Coming soon.

media coverage

  • The Answer To Why Emotionally Worded Prompts Can Goose Generative AI Into Better Answers And How To Spur A Decidedly Positive Rise Out Of AI, by Forbes. November 2023. website
  • CulturePark for low-resource large language models, by MIT Technology Review. June 2024. website
  • EmotionPrompt in RAG, by LlamaIndex. August 2023. website
  • Exploring the effects of emotional stimuli to large language models, by TexExplore. September 2023. website

selected publications

  1. emotion_all.png
    The good, the bad, and why: Unveiling emotions in generative ai
    Cheng Li, Jindong Wang, Yixuan Zhang, and 7 more authors
    In International Conference on Machine Learning (ICML), 2024
    arXiv Code
  2. culturellm.png
    Culturellm: Incorporating cultural differences into large language models
    Cheng Li, Mengzhou Chen, Jindong Wang, and 2 more authors
    In Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
    arXiv Code
  3. culturepark.png
    CulturePark: Boosting Cross-cultural Understanding in Large Language Models
    Cheng Li, Damien Teney, Linyi Yang, and 3 more authors
    In Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
    arXiv Code
  4. mentalarena.png
    MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders
    Cheng Li, May Fung, Qingyun Wang, and 4 more authors
    In ArXiv, 2024
    arXiv