Steffi Chern
🎓 Hi everyone! I’m Steffi, currently an undergraduate senior studying Statistics and Machine Learning at Carnegie Mellon University, seeking opportunities to pursue a Ph.D. degree in NLP/ Computer Science starting Fall 2024.
✨ My research interests lie at the intersection of natural language processing (NLP) and machine learning (ML). I’m particularly interested in developing rigorous evaluations of large language models (LLMs) that delve deeper than surface-level task performance.
🚀 In this rapidly evolving field, I strive to contribute towards establishing more reliable and comprehensive evaluation frameworks to better understand the capabilities and limitations of existing AI systems, thereby enhancing their trustworthiness and ensuring their behaviors follow human intentions.
⛳ I’m also a student-athlete, playing NCAA Women’s Golf at Carnegie Mellon University.
⬇️ Below are some of my recent publications:
Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate
Steffi Chern, Ethan Chern, Graham Neubig, Pengfei Liu
Preprint. [paper] [github]
FacTool: Factuality Detection in Generative AI - A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios
I-Chun Chern, Steffi Chern, Shiqi Chen, Weizhe Yuan, Kehua Feng, Chunting Zhou, Junxian He, Graham Neubig, Pengfei Liu
Preprint. [paper] [github] [website]
Combating Adversarial Attacks with Multi‑Agent Debate
Steffi Chern *, Zhen Fan *, Andy Liu *
Preprint. [paper]
Align on the Fly: Adapting Chatbot Behavior to Established Norms
Chunpu Xu, Steffi Chern, Ethan Chern, Ge Zhang, Zekun Wang, Ruibo Liu, Jing Li, Jie Fu, Pengfei Liu
Preprint. [paper] [github]
Voice Direction‑of-Arrival Conversion
I‑Chun Chern, Steffi Chern, Heng‑Cheng Kuo, Huan‑Hsin Tseng, Kuo‑Hsuan Hung, Yu Tsao
Accepted to 33rd IEEE Machine Learning for Signal Processing (MLSP) 2023. [paper]
Automated Analysis of Fluency Behaviors in Aphasia.
Davida Fromm, Brian MacWhinney, Steffi Chern, Zihan Geng, Mason Kim, Joel Greenhouse
Accepted to 52nd Clinical Aphasiology Conference (CAC). [poster] [paper]
đź“© Feel free to contact me about any research/job opportunities or questions you have!