Home | Etha Tianze Hua

I am a PhD student in Computer Science at Brown University, where I am fortunate to be advised by 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 computational models, two components are required: (a) operationalized definitions of those cognitive properties, and (b) sufficient knowledge of the inner workings of the computational models 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 direction, interpretability, where concrete answers are achievable.

Updates

Aug 2026Our work "Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts" got accepted into Findings of EMNLP 2026!
Jul 2026Our work "Source Modality Monitoring in Vision-Language Models" got accepted into COLM 2026!
May 2026Started my summer internship at Kensho's R&D team, working on evaluating LLM agents.
Aug 2025We presented our work "How Do Vision-Language Models Process Conflicting Information Across Modalities?" at NEMI'25 in Boston, MA.
May 2025I will be officially joining the LUNAR lab as a PhD student starting this Fall!
Jun 2024We presented our NAACL'24 work in Mexico City, Mexico.
Mar 2024Our work "mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?" got accepted into Findings of NAACL 2024!
Aug 2023I attended the Cornell, Maryland, Max Planck Pre-doctoral Research School 2023 in Saarbrücken, Germany.

Publications

Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts

Athulith Paraselli, Tianze Hua, and Ellie Pavlick

Findings of EMNLP 2026 Code Project Page

BibTeX

@misc{paraselli2026slowseeslowsuppress,
      title={Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts}, 
      author={Athulith Paraselli and Etha Tianze Hua and Ellie Pavlick},
      year={2026},
      eprint={2609.00293},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2609.00293}, 
}

Source Modality Monitoring in Vision-Language Models

Tianze Hua, Tian Yun, and Ellie Pavlick

COLM 2026 Code Project Page

BibTeX

@misc{hua2026sourcemodalitymonitoringvisionlanguagemodels,
      title={Source-Modality Monitoring in Vision-Language Models}, 
      author={Etha Tianze Hua and Tian Yun and Ellie Pavlick},
      year={2026},
      eprint={2604.22038},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2604.22038}, 
}

How Do Vision-Language Models Process Conflicting Information Across Modalities?

Tianze Hua*, Tian Yun*, and Ellie Pavlick

ArXiv Preprint Code Project Page

BibTeX

@misc{hua2025visionlanguagemodelsprocessconflicting,
      title={How Do Vision-Language Models Process Conflicting Information Across Modalities?}, 
      author={Tianze Hua and Tian Yun and Ellie Pavlick},
      year={2025},
      eprint={2507.01790},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2507.01790}, 
}

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

BibTeX

@inproceedings{hua-etal-2024-mothello,
    title = "m{O}thello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?",
    author = "Hua, Tianze  and
      Yun, Tian  and
      Pavlick, Ellie",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-naacl.103/",
    doi = "10.18653/v1/2024.findings-naacl.103",
    pages = "1585--1598"
}

Education

2025–: Ph.D. Computer Science, Brown University
2023–2025: Sc.M. Computer Science, Brown University
2019–2023: B.S. Computer Science & Philosophy, Tufts University