Tianze (Etha) Hua

I am a second-year master's student at Brown University, working with Professor Ellie Pavlick.

My research focuses on interpretability and human-model comparison. I believe for us to attribute cognitive properties (m knows p, m understands English, m is conscious, and etc.) to AI systems, two components are required: (a) operationalized definitions of those cognitive properties, and (b) sufficient knowledge of the inner workings of the AI systems of interest. While the first component has been the subject of lengthy debates in philosophy of mind / epistemology and may remain unresolved, the second component offers a domain, interpretability, where concrete answers are achievable.

To get a better understanding of the internal mechanisms in LLMs, I am currently investigating the modularity of representations and circuits in transformer models.

Besides interpretability, I am also interested in experimenting and analyzing language understanding through multi-agent interactions.

Updates

• June 2024: We presented our NAACL'24 work in Mexico City, Mexico.
• March 2024: Our work "mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?" got accepted into Findings of NAACL 2024!
• August 2023: I attended the Cornell, Maryland, Max Planck Pre-doctoral Research School 2023 in Saarbrücken, Germany.

Publications

• mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?
  Tianze Hua*, Tian Yun*, and Ellie Pavlick
  Findings of NAACL 2024 [Code] [Project Page]

Education

2023-now

Sc.M. Computer Science, Brown University

2019-2023

B.S. Computer Science & Philosophy, Tufts University

some other cool stuffs

> A tree defined by a Lindenmayer system.

> Order and chaos generated with the rule110 cellular automaton.