sunniesuhyoung

sunniesuhyoung, 9 days ago to random

📢 Recruiting for a paid study about large language models (LLMs)

We're looking for US-based adult participants for a 1 hour study on Zoom (payment: $15 Amazon gift card). Open to diverse range of knowledge/experience with LLMs.

If interested, please fill out 👇
https://forms.gle/6aGfJNrfhpuQzmz59

RT appreciated!

sunniesuhyoung, 11 days ago to random

If you are #FAccT2024, please join the trust and reliance session tomorrow (Wednesday) at 11:35am in the Sao Conrado room to hear from me, Naina Balepur, Arianna Manzini, @ruotongw, and Ziyang Guo

Program 📃: https://programs.sigchi.org/facct/2024/my-schedule/session/164930

I'll talk about LLMs' uncertainty expression and its impact on (over)reliance/trust

Paper 🧵: https://hci.social/@sunniesuhyoung/112374090391640712

sunniesuhyoung, 24 days ago to random

In case @andresmh doesn't brag about this 🙈 Andrés received a graduate mentoring award for being the most amazing mentor!!!

https://www.princeton.edu/news/2024/05/21/faculty-members-honored-excellence-mentoring-graduate-students

sunniesuhyoung, 1 month ago to random

I am at #CHI2024 for the Doctoral Consortium and the #HCXAI workshop. I do AI+HCI research on transparency, explainability, and trust in AI and would love to chat! I'm also graduating next spring and will be looking for jobs soon 👩🏻‍💻

https://programs.sigchi.org/chi/2024/program/content/151003

sunniesuhyoung, 1 month ago to random

There is a lot of interest in estimating LLMs' uncertainty, but should LLMs express uncertainty to end users? If so, when and how?

In our #FAccT2024 paper, we explore how users perceive and act upon LLMs’ natural language uncertainty expressions.

https://arxiv.org/abs/2405.00623

1/6