Cathy Jiao



Hello! I am a grad student in the Language Technologies Institute at Carnegie Mellon University, where I am advised by Maxine Eskenazi and Aaron Steinfeld.

My research interest is in natural language processing. In particular, I have been working on dialogue in two different realms: first, I am exploring language model capabilities on various aspects of dialogue. Second, I am working to expand accessibility in dialogue systems (e.g., trying to improve dialogue systems for people with disabilities).

Before I came to CMU, I worked at Motorola Solutions, where I created NLP tools for text/video public safety applications. Prior to that, I did my B.Sc. in computer science and mathematics at the University of British Columbia.


09/2022 Demoed our DialPort Portal and Dashboard tools as part of our paper at SIGDIAL.
05/2022 One workshop paper accepted to CVPR! Our work explored enhancing model generalization in embodied instruction following.
05/2022 We released the paper and code for InstructDial, an instruction tuning framework for dialogue-related tasks. Along with the 48 dialogue tasks we provided in the repository, we encourage people to use the framework for other dialogue-related tasks.
03/2022 Patent granted for my undergrad internship project at Motorola Solutions.
08/2021 Started grad school at CMU.


*= equal contribution

  1. Understanding the Effectiveness of Very Large Language Models on Dialog Evaluation
    Jessica Huynh,  Cathy Jiao, Prakhar Gupta, Shikib Mehri, Payal Bajaj, Vishrav Chaudhary,  and Maxine Eskenazi
    To appear at IWSDS 2023
  2. Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning
    Prakhar Gupta,  Cathy Jiao, Yi-Ting Yeh, Shikib Mehri, Maxine Eskenazi,  and Jeffrey P. Bigham
    EMNLP 2022
  3. Improving compositional generalization for multi-step quantitative reasoning in question answering
    Armineh Nourbakhsh,  Cathy Jiao, Sameena Shah,  and Carolyn Rosé
    EMNLP 2022
  4. The DialPort tools
    Jessica Huynh*, Shikib Mehri*,  Cathy Jiao*,  and Maxine Eskenazi
    SIGDIAL 2022
  5. ET tu, CLIP? Addressing Common Object Errors for Unseen Environments
    Ye Won Byun*,  Cathy Jiao*, Shahriar Noroozizadeh*, Jimin Sun*,  and Rosa Vitiello*
    CVPR, Embodied AI Workshop, 2022


  1. Natural language text conversion and method therefor
    Roger Donaldson,  and Cathy Jiao
    U.S. Patent 11275906, 2022