Hi there. I am 1st year MSCS student at University of Illinois Urbana-Champaign, honered to be advised by Prof. Heng Ji. My research interest mainly focus on Natural Language Processing and Large Language Models.

Research Interest

I have a wide interest in NLP. Currently, I am focusing on the following topics:

Knowledge in Language Models Given that LLMs can serve as knowledge bases, I want to explore how the knolwedges are stored in LLMs. My goal is to help LLMs understand and utilize the knowledge in a better way.
Language Models’ Explainability and Interpretability LLMs's behaviors are always unpredictable and unorganzied, I hope to help the community understanding LLMs from an intrinsic perspective.

Besides, I am also quite interested in Multi-Modal Learning.

Publication

† denotes equal contribution

2024

• Why Does New Knowledge Create Messy Ripple Effects in LLMs?

  Jiaxin Qin, Zixuan Zhang, Chi Han, Pengfei Yu, Manling Li, Heng Ji

  EMNLP 2024 Short [paper] [bib] [poster]

  
  

  @article{qin2024does,
    title={Why Does New Knowledge Create Messy Ripple Effects in LLMs?},
    author={Qin, Jiaxin and Zhang, Zixuan and Han, Chi and Li, Manling and Yu, Pengfei and Ji, Heng},
    journal={arXiv preprint arXiv:2407.12828},
    year={2024}
  }               
                    
                      

2023

• H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation.

  Yanjie Ze, Yuyao Liu†, Ruizhe Shi†, Jiaxin Qin, Zhecheng Yuan, Jiashun Wang, Huazhe Xu

  NeurIPS 2023 [paper] [bib]

  
  

  @article{ze2023h,
    title={H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation},
    author={Ze, Yanjie and Liu, Yuyao and Shi, Ruizhe and Qin, Jiaxin and Yuan, Zhecheng and Wang, Jiashun and Xu, Huazhe},
    journal={arXiv preprint arXiv:2310.01404},
    year={2023}
  }
                      

• Towards Effective Ancient Chinese Translation: Dataset, Model, and Evaluation.

  Geyang Guo, Jiarong Yang, Fengyuan Lu, Jiaxin Qin, Tianyi Tang, Wayne Xin Zhao

  NLPCC 2023 [paper] [bib]

  
  

  @inproceedings{guo2023towards,
    title={Towards Effective Ancient Chinese Translation: Dataset, Model, and Evaluation},
    author={Guo, Geyang and Yang, Jiarong and Lu, Fengyuan and Qin, Jiaxin and Tang, Tianyi and Zhao, Wayne Xin},
    booktitle={CCF International Conference on Natural Language Processing and Chinese Computing},
    pages={416--427},
    year={2023},
    organization={Springer}
  }