Hi! I graduated from SJTU (Shanghai Jiaotong University) in 2024.6. I’m fortunate to be advised by Prof. Junxian He during my undergraduate period. I am also a first year PhD candidate at HKUST NLP supervised by Junxian He!

I am broadly interested in natural language processing and machine learning. Currently, I am focused on

• Hallucination in VLM
• Hallucination and truthfulness of LLM from an interpretability perspective.

Experience

2023.6-2023.12 Internship in ShanghaiAI Lab advised by Prof. Yu Cheng.

Publication

On the Universal Truthfulness Hyperplane Inside LLMs

Junteng Liu, Shiqi Chen, Yu Cheng, Junxian He (Accepted by EMNLP 2024 main)

Github Code

In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation

Shiqi Chen, Miao Xiong, Junteng Liu, Zhengxuan Wu, Teng Xiao, Siyang Gao, Junxian He (Accepted by ICML 2024)

C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models

Yuzhen Huang, Yuzhuo Bai, Zhihao Zhu, Junlei Zhang, Jinghan Zhang, Tangjun Su, Junteng Liu, Chuancheng Lv, Yikai Zhang, Jiayi Lei, Yao Fu, Maosong Sun, Junxian He (Accepted by NeurIPS 2023)

Composing Parameter-Efficient Modules with Arithmetic Operations

Jinghan Zhang, Shiqi Chen, Junteng Liu, Junxian He (Accepted by NeurIPS 2023)

Award

Zhiyuan Honor Scholarship