profile image

Chan Young Park

Postdoctoral Researcher
Microsoft Research
park (at) utexas.edu
she/her


šŸŽ“ I will be starting as an Assistant Professor at UT Austin Information School in Fall 2026 and am looking for 1-2 PhD students this admission cycle. Candidates should have a strong technical background in NLP and Human-centered AI. If interested, please fill out this form to show your interest.

I'm a postdoctoral researcher in the AI Interaction and Learning team at Microsoft Research. Previously, I was a postdoc working with Yejin Choi at the University of Washington. I received my PhD from Language Technologies Institute at Carnegie Mellon University, advised by Yulia Tsvetkov. I am a recipient of K&L Gates Presidential Fellowship and KFAS Fellowship, and was selected as UChicago Rising Stars in Data Science. I was a research intern at Meta AI and Adobe Research. For more information, please check my CV.

Research Interests

My research interests are in the area of NLP, AI Ethics, and computational social science. Specifically, my research aims to build adaptable and personalized NLP systems for individuals and groups, with a focus on making technologies both more effective and equitable. Additionally, I develop frameworks to analyze social biases and fairness in AI systems, and work on bridging the gap between CS and CSS to facilitate the adoption of cutting-edge AI models in other disciplines.

News

Nov 2024 šŸŽ¤ I was invited to give a talk at the Second Workshop on Social Influence in Conversations@EMNLP 2024!
Sep 2024 šŸŽ¤ Excited to start my postdoc with Prof. Yejin Choi, working on LLMs for robotics that incorporate physical knowledge
Oct 2023 šŸ† I'm selected as a recipient of the K&L Gates Presidential Fellowship in Ethics and Computational Technologies.
Oct 2023 šŸŽ¤ I'm co-organizing Customizable NLP workshop. Join us at EMNLP 2024!
Aug 2023 šŸ“° My research and my interview was featured in MIT Technology Review and Washington Post.
Aug 2023 šŸŽ¤ I'm serving as an area chair of the Ethics track of EMNLP 2023.
Jul 2023 šŸ† Our paper on political biases of LLMs received the best paper award at ACL 2023!!
Jun 2023 šŸ† Our paper on social biases in Wikipedia was selected as Wikimedia Foundation Research Award of the Year 2023.
Oct 2022 šŸ† I was selected as UChicago Rising Stars in Data Science.
Aug 2022 šŸ“ Our new PNAS paper on emotion analysis of 2019 #BLM movement tweets is now available! It was covered by UW and CMU News too!

Publications


(*) Equal Contribution
Filter by: Personalization Bias & Fairness AI Alignment AI Ethics Computational Social Science

    2025

  1. CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring the (Lack of) Cultural Knowledge of LLMs
    Yu Ying Chiu, Liwei Jiang, Bill Yuchen Lin, Chan Young Park, Shuyue Stella Li, Sahithya Ravi, Mehar Bhatia, Maria Antoniak, Yulia Tsvetkov, Vered Shwartz, Yejin Choi
    ACL PDF Tags: Bias & Fairness, Computational Social Science
  2. SPICA: Retrieving Scenarios for Pluralistic In-Context Alignment
    Quan Ze Chen, K.J. Kevin Feng, Chan Young Park, Amy X. Zhang
    ACL Findings PDF Tags: Personalization, Bias & Fairness, AI Alignment
  3. Political Neutrality in AI is Impossible- But Here is How to Approximate it
    Jillian Fisher, Ruth E. Appel, Chan Young Park, Yujin Potter, Liwei Jiang, Taylor Sorensen, Shangbin Feng, Yulia Tsvetkov, Margaret E. Roberts, Jennifer Pan, Dawn Song, Yejin Choi
    ICML PDF Tags: AI Ethics, Bias & Fairness, AI Alignment
  4. ComPO: Community Preferences for Language Model Personalization
    Chan Young Park*, Sachin Kumar*, Yulia Tsvetkov, Noah A Smith, Hannaneh Hajishirzi
    NAACL PDF Tags: Personalization, AI Alignment

    5. 2024

  5. ValueScope: Unveiling Implicit Norms and Values via Return Potential Model of Social Interactions
    Chan Young Park*, Shuyue Stella Li*, Hayoung Jung*, Svitlana Volkova, Tanushree Mitra, David Jurgens, Yulia Tsvetkov
    EMNLP Findings PDF Tags: Computational Social Science
  6. Locating Information Gaps and Narrative Inconsistencies Across Languages: A Case Study of LGBT People Portrayals on Wikipedia
    Farhan Samir, Chan Young Park, Anjalie Field, Vered Shwartz, Yulia Tsvetkov
    EMNLP MSN News PDF Tags: Computational Social Science, Bias & Fairness
  7. Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration
    Shangbin Feng, Taylor Sorensen, Yuhan Liu, Jillian Fisher, Chan Young Park, Yejin Choi, Yulia Tsvetkov
    EMNLP PDF Tags: AI Alignment, Personalization
  8. What Constitutes a Faithful Summary? Preserving Author Perspectives in News Summarization
    Yuhan Liu, Shangbin Feng, Xiaochuang Han, Vidhisha Balachandran, Chan Young Park, Sachin Kumar, Yulia Tsvetkov
    NAACL PDF Tags: Bias & Fairness
  9. Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions
    Sachin Kumar, Chan Young Park, Yulia Tsvetkov
    ICLR PDF Tags: Personalization

    10. 2023

  10. TalkUp: Paving the Way for Understanding Empowering Language
    Chan Young Park*, Lucille Njoo*, Octavia Stappart, Marvin Thielk, Yi Chu, Yulia Tsvetkov
    EMNLP Findings PDF Data Tags: Computational Social Science
  11. Analyzing Norm Violations in Live-Stream Chat
    Jihyung Moon, Dong-Ho Lee, Hyundong Cho, Woojeong Jin, Chan Young Park, Minwoo Kim, Jonathan May, Jay Pujara, Sungjoon Park
    EMNLP PDF Tags: Computational Social Science
  12. From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models
    Shangbin Feng, Chan Young Park, Yuhan Liu, Yulia Tsvetkov
    ACL PDF MIT Tech Review Washington Post Best Paper Award Tags: Bias & Fairness, AI Ethics

    13. 2022

  13. Challenges in Opinion Manipulation Detection: An Examination of Wartime Russian Media
    Chan Young Park*, Julia Mendelsohn*, Anjalie Field*, Yulia Tsvetkov
    EMNLP Findings PDF Tags: Computational Social Science
  14. An Analysis of Emotions and the Prominence of Positivity in #BlackLivesMatter Tweets
    Chan Young Park*, Anjalie Field*, Antonio Theophilo*, Jamelle Watson-Daniels, Yulia Tsvetkov
    Proceedings of the National Academy of Sciences, 2022.
    PNAS PDF CMU News Tags: Computational Social Science
  15. Controlled Analyses of Social Biases in Wikipedia Bios
    Anjalie Field, Chan Young Park, Kevin Z. Lin, Yulia Tsvetkov
    WWW PDF Wikimedia Research of the Year Tags: Computational Social Science, Bias & Fairness

    16. 2021

  16. Detecting Community Norm Violations in Online Conversations
    Chan Young Park, Julia Mendelsohn, Karthik Radhakrishnan, Jain, Tushar Kanakagiri, David Jurgens, Yulia Tsvetkov
    EMNLP Findings PDF Tags: Computational Social Science
  17. Multilingual Contextual Affective Analysis of LGBT People Portrayals in Wikipedia
    Chan Young Park*, Xinru Yan*, Anjalie Field*, Yulia Tsvetkov
    ICWSM PDF Talk Slides Tags: Computational Social Science, Bias & Fairness
  18. Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks
    Chan Young Park*, Jimin Sun*, Hwijeen Ahn*, Yulia Tsvetkov, David R Mortensen
    EACL PDF Code Tags: Computational Social Science, Multilinguality

    19. ~2020

  19. NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfer
    Chan Young Park*, Hwijeen Ahn*, Jimin Sun*, Jungyun Seo
    Proceedings of the Fourteenth Workshop on Semantic Evaluation, 2020.
    SemEval@EMNLP PDF Code Poster Tags: Multilinguality
  20. Learning to Generate Word- and Phrase-Embeddings for Efficient Phrase-Based Neural Machine Translation
    Chan Young Park, Yulia Tsvetkov
    Proceedings of the 3rd Workshop on Neural Generation and Translation, 2019.
    WNGT@EMNLP PDF Code Tags: NLP
  21. Attention-based dialog embedding for dialog breakdown detection
    Chan Young Park, Kyungduk Kim, Songkuk Kim
    Proceedings of the dialog system technology challenges workshop, 2019.
    DSTC6 PDF Tags: NLP