Sunnie
S. Y. Kim

I'm a senior researcher at Microsoft Research NYC in the Sociotechnical Systems group (FATE, STAC, SMC). I work on responsible AI, human-AI interaction, and AI evaluation. I'm particularly interested in measuring and mitigating interaction risks (e.g., overreliance on AI) and improving human-AI workflows for responsible AI development. See my talk on fostering appropriate reliance on LLMs.

My research has been published in top AI, HCI, and FATE venues, recognized with paper awards, and featured in media outlets. I have also received several honors including the NSF Graduate Research Fellowship, the Rising Stars in EECS Recognition, the Siebel Scholars Award, and the Korea Presidential Science Scholarship.

Prior to joining Microsoft, I was a senior research scientist at Apple in the Human-Centered Machine Learning & Responsible AI group. I received a PhD in Computer Science from Princeton University where I worked with Olga Russakovsky and Andrés Monroy-Hernández, and a BSc in Statistics and Data Science from Yale University where I worked with John Lafferty and Jay Emerson.

My first name is pronounced like sunny 🔆 and I use she/her/hers pronouns. S. Y. comes from my Korean name, Suh Young (서영). In my free time, I run, play tennis, and enjoy Korean books and music.

  CV

News

05/2026: Joined Microsoft Research NYC as a senior researcher in the Sociotechnical Systems group!
05/2026: New paper on LLM evaluation. It analyzes the prevalence, potential effects, and controllability of human-like behaviors in LLMs.
04/2026: New paper at FAccT 2026. It is about understanding annotators' safety policies (what they consider safe vs. unsafe AI outputs) from labeling behavior alone using interpretable models.
02/2026: New paper at CHI 2026. It is about how different messages about LLMs found in public discourse can shape how people think about and interact with LLMs.
01/2026: Serving as an AC for CHI and FAccT this year.
09/2025: Visited Pittsburgh and gave talks on fostering appropriate reliance on LLMs at CMU's responsible AI reading group and the NSF workshop on human-AI complementarity.
This Past Year: Had a lovely time visiting and giving talks (some virtually) at KAIST, MILA, Cornell Tech, SNU, Johns Hopkins, BU, Cornell, Apple, Yonsei University, and NAVER.

Selected papers

See the full list of papers here

Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts
Sunnie S. Y. Kim, Margit Bowler, Leon A Gatys
PAPER

Presenting Large Language Models as Companions Affects What Mental Capacities People Attribute to Them
Allison Chen, Sunnie S. Y. Kim, Angel Nathaniel Franyutti-Cintron, Amaya Dharmasiri, Kushin Mukherjee, Olga Russakovsky, Judith E. Fan
CHI 2026 ● PAPER

Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies
Sunnie S. Y. Kim, Jennifer Wortman Vaughan, Q. Vera Liao, Tania Lombrozo, Olga Russakovsky
CHI 2025 HONORABLE MENTION ● PAPER ● TALK

* Featured in Microsoft's New Future of Work report and presented at 10+ places through invited and contributed talks.

"I'm Not Sure, But...": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust
Sunnie S. Y. Kim, Q. Vera Liao, Mihaela Vorvoreanu, Stephanie Ballard, Jennifer Wortman Vaughan
FAccT 2024 ● PAPER ● OSF

* Featured in Axios, New Scientist, ACM showcase, Microsoft's New Future of Work and Responsible AI Transparency reports, and the Human-Centered AI Medium publication as Good Reads in Human-Centered AI.

"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction
Sunnie S. Y. Kim, Elizabeth Anne Watkins, Olga Russakovsky, Ruth Fong, Andrés Monroy-Hernández
CHI 2023 HONORABLE MENTION ● PAPER ● WEBSITE ● TALK

* One of the top 10 cited CHI papers in 2023-2024 (as of Dec 2024). Featured in the Human-Centered AI Medium publication as CHI 2023 Editors' Choice. Also presented at the NeurIPS 2022 Human-Centered AI Workshop (spotlight), CHI 2023 Human-Centered Explainable AI Workshop (spotlight), ECCV 2024 Explainable Computer Vision Workshop (invited talk), and NYC Computer Vision Day 2024 (lightning talk).

Other important things

Organizing Committee
●  IUI 2027, Publicity/Web Co-Chair
●  FAccT 2025, Proceedings Co-Chair
●  CVPR 2025 Workshop on Explainable AI for Computer Vision (XAI4CV), Co-Organizer
●  NYC Computer Vision Day 2025, Event Program Committee
●  CVPR 2024 Workshop on Explainable AI for Computer Vision (XAI4CV), Co-Organizer
●  CHI 2024 Workshop on Human-Centered Explainable AI (HCXAI), Co-Organizer
●  CVPR 2023 Workshop for Women in Computer Vision (WiCV), Co-Organizer
●  CVPR 2023 Workshop on Explainable AI for Computer Vision (XAI4CV), Co-Organizer
●  NESS NextGen Data Science Day 2018, Local Organizing Committee

Program Committee & Reviewing
●  CHI (2023, 2024, 2025, 2026 AC of Computational Interaction subcommittee)
●  FAccT (2023, 2024, 2025, 2026 AC), AIES (2024), SaTML (2023)
●  NeurIPS (2025 Main track & Ethics review, 2026 Main track)
●  CVPR (2022, 2023, 2024, 2025), ICCV (2021, 2023), ECCV (2022, 2024)
●  Various workshops at NeurIPS, CHI, CVPR, ICML, AAAI, IUI (2021—Now)
●  ML Reproducibility Challenge (2020, 2021, 2022)

Mentoring
●  Alex Oesterling, CS PhD student at Harvard, 2025—2026
●  Allison Chen, CS PhD student at Princeton, 2024—2025
●  Indu Panigrahi, CS Master's student at Princeton, Now CS PhD student at UIUC, 2024—2025
●  Rohan Jinturkar, CS Undergrad at Princeton, Now Engineer at Open AI, 2022—2023
●  Nicole Meister, CS Undergrad at Princeton, Now EE PhD student at Stanford, 2020—2022
●  Sharon Zhang, CS Undergrad at Princeton, Now CS PhD student at Stanford, 2020—2021
●  Princeton Computer Science G1 Mentoring Program, 2022—2023
●  Princeton Computer Science Graduate Applicant Support Program, 2021—2022

Teaching
●  Princeton Computer Science 429 Computer Vision, Graduate TA, 2021
●  Princeton AI4ALL, Instructor, 2021
●  TTI-Chicago Girls Who Code, Instructor & Co-Founder, 2019—2020
●  Yale Statistics & Data Science 365/565 Data Mining and Machine Learning, Undergraduate TA, 2018
●  Yale Statistics & Data Science 230/530 Data Exploration and Analysis, Undergraduate TA, 2017

Community Building & More
●  FAccT, CVPR, ECCV, NeurIPS, ICLR, NSF SafeTAI Workshop, Student Volunteer, 2019—2024
●  Explainable AI Slack and Twitter Community, Co-Organizer, 2022—2023
●  Princeton Computer Science Graduate Admissions Committee, Application Reviewer, 2021
●  COVID Translate Project, Volunteer Translator, 2020
●  Yale Dimensions Organization for Women and Other Minorities in Math, Co-Founder, 2017—2019
●  Yale S&DS Departmental Student Advisory Committee, Co-Founding Member, 2017—2019

Please reach out!

●  I was on the academic and industry job market (2024—2025 cycle). During this time, I received support from countless people, including people I haven't met before. Happy to be a resource and share anything that would be helpful.
●  I benefited from various mentoring programs in grad school (e.g., doctoral consortiums and the Rising Stars in EECS workshop). I would be excited to contribute back as a mentor or in other ways.
●  I enjoy co-organizing and participating in workshops, tutorials, panels, etc., especially those focused on connecting different communities.
●  Please reach out if any of these apply! :)

Contact

sunniesuhyoung [at] gmail.com
google scholar
linkedin
github
bluesky
mastodon
twitter/X

Website template credit to Abhraneel