Bingxiang He

This is Bingxiang He’s personal homepage.

Biography

I am a fourth-year undergraduate student studying at Tsinghua University, majoring in Computer Science and Technology. I am a member of THUNLP, advised by Prof. Zhiyuan Liu. My research interests primarily lie in the field of natural language processing, with a particular focus on save and robust pre-trained language models.

My first scientific research project is about text backdoor attack and defense. In recent years, many attack and defense models have emerged in the field of text backdoor attack and defense, but there is a lack of a unified implementation and standard evaluation platform in the field of backdoor attack. Therefore, we launched the text backdoor attack and defense toolkit OpenBackdoor, which integrates a large number of existing attack and defense algorithms, and also introduced a backdoor defense method CUBE.

Looking forward, I am going to be a Ph.D. student in THUNLP Lab, Dept. of Computer Science and Technology, Tsinghua University, also advised by Prof. Zhiyuan Liu, starting from Fall 2024.

Research Highlights:

  • Committed to build safe and robust large language models.

Publications

(*indicates equal contribution)

  • A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks [Paper] (Spotlight)
    Ganqu Cui*, Lifan Yuan*, Bingxiang He, Yangyi Chen, Zhiyuan Liu, Maosong Sun.
    NeurIPS Datasets & Benchmarks 2022 [code]
  • Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT [Paper]
    Biru Zhu, Lifan Yuan, Ganqu Cui, Yangyi Chen, Chong Fu, Bingxiang He, Yangdong Deng, Zhiyuan Liu, Maosong Sun, Ming Gu.
    EMNLP 2023 Main [code]
  • UltraFeedback: Boosting Language Models with High-quality Feedback [Paper]
    Ganqu Cui*, Lifan Yuan*, Ning Ding, Guanming Yao, Bingxiang He, Wei Zhu, Yuan Ni, Guotong Xie, Ruobing Xie, Yankai Lin, Zhiyuan Liu, Maosong Sun.
    ICML 2024 In Submission
  • Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents [Paper]
    Cheng Qian*, Bingxiang He*, Zhong Zhuang, Jia Deng, Yujia Qin, Xin Cong, Zhong Zhang, Jie Zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun.
    ACL 2024 In Submission [code]

For more information

More info about me can be found in CV or downloaded CV.