| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Fri, 28 Nov 2025 09:30:18 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"69296baa-3b74"
expires: Mon, 29 Dec 2025 02:58:03 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 502B:2C10E1:8334CC:937098:6951EBE3
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 02:48:03 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210054-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766976483.420191,VS0,VE201
vary: Accept-Encoding
x-fastly-request-id: 4549418eb9cff178770b372a07236d879c895941
content-length: 5980
Jieyu Zhao
Office: USC GCS #405A
Email: 
[at] usc [dot] edu
Last Update:
Jieyu Zhao θ΅΅ζ΄η
Gabilan Assistant Professor
Thomas Lord Department of Computer Science, USC
Jieyu Zhao is an Assistant Professor of Computer Science Department at University of Southern California. Prior to that, she was an NSF Computing Innovation Fellow at University of Maryland, College Park, working with Prof. Hal DaumΓ© III. Jieyu received her Ph.D. from Computer Science Department, UCLA, where she was advised by Prof. Kai-Wei Chang. Her research interest lies in fairness of ML/NLP models. Her paper got the EMNLP Best Long Paper Award (2017). She was one of the recipients of 2020 Microsoft PhD Fellowship and has been selected to participate in 2021 Rising Stars in EECS workshop. Her research has been covered by news media such as Wired, The Daily Mail and so on. She was invited by UN-WOMEN Beijing on a panel discussion about gender equality and social responsibility. Her CV is available here.
πΎ Research | π Papers | πβπ© Lab
I am broadly interested in research about how to get machines to understand and respond to human languages (natural language processing & machine learning). A few questions that drive my recent research are:
- How can we get models to efficiently learn knowledge? We develop post-training methods, including efficient fine-tuning, reinforcement learning from feedback (RLHF/RFT), and scalable agentic architectures to help LLMs learn new knowledge with minimal computational cost
- How can we rigorously evaluate model capabilities and limitations? We design comprehensive evaluation frameworksβcovering reasoning, safety, cultural intelligence, and agentic behaviorsβto better understand when and why models fail, and how to guide them toward more reliable performance.
- How can we reduce potential risks from the model? Our work introduces techniques to evaluate and mitigate biases, hallucinations, privacy leakage, and other safety concerns in LLMs, ultimately leading to more reliable and robust models.
- How can we advance better models and humans collaborations? We study how LLMs interact with people from diverse social and cultural backgrounds, and examine how AI can meaningfully support interdisciplinary applicationsβsuch as education, healthcare, and beyond.
π’ Attention:
- [PhD 2026] I am looking for PhD students to join my research group. But I'm still waiting for the university's guidance about PhD recruitment. I cannot make any promise at this moment. But if it is allowed, I'd anticipate to get 1-2 PhDs.
- If you are interested in doing research with my group, please check this first.
- If you want to request a recommendation letter, please fill in this form at least 3 weeks in advance.
π° Recent News
- [Nov 2025] I will be at IVADO workshop.
- [Nov 2025] π Thrilled to annouce our paper Analyzing Uncertainty of LLM-as-a-Judge won the SAC highlight at EMNLP! Congrats to all collaborators!
- [Nov 2025] I will be at EMNLP 2025. See you there!
- [Oct 2025] π©π»βπ» I gave a talk at UPenn CLunch on 'Building Personalized AI Assistants: From Task Execution to Human Alignment'.
- [Oct 2025] π Congrats to Taiwei for passing his PhD qual exam. He is a PhD candidate now!
- [Aug 2025] π We got 5 papers accepted at EMNLP 2025! Check them out here.
- [Aug 2025] π Congrats on Linxin's CoAct-1 getting No.1 on OSWorld! Check the news coverage here.
- [Aug 2025] π©π»βπ» I gave a talk at Academic Conference on Intersection of AI & Gender hosted by UNWomen, Korea!
- [Jul 2025] π Congrats to @Linxin Song for his SEA paper accepted at COLM 25!
- [Jun 2025] π©π»βπ» I will give a talk at USC Viterbi Chat: Seattle on Jun 11th. Happy chatting with you there!
- [Jun 2025] π Congrats to @Zhaotian Weng for getting the USC Viterbi Graduate Award.
- [May 2025] π Honored to be listed as one of 100 Brilliant Women in AI Ethics.
- [Apr 2025] π Congrats to @Jiazhi Li for passing his PhD defense! Great job, Dr. Li!
- [Mar 2025] π©π»βπ» Talk at Linguistics Department @ USC.
- [Mar 2025] π©π»βπ« Starting from 2025 March, I set aside 30 mins every Friday to meet with anyone. Free free to sign up here if you would like to chat with me on any topics.
- [Jan 2025] π©π»βπ« Guest lecture at Global AI Regulation Class. USC Law School.
ποΈοΈ More News
- [Dec 2024] I will be at NeurIPS from Dec.9 - 12. Hope to chat with you there!
- [Nov 2024] I will be at EMNLP from Nov. 11 - Nov. 16. Hope to chat with you!
- [Nov 2024] I gave a talk at UCLA NLP Seminar. It was great to see some old and new friends there!
- [Oct 2024] Please check our papers that are going to be presented at EMNLP 2024:
- InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Context
- Self-Contradictory Reasoning Evaluation and Detection
- Images Speak Louder than Words: Understanding and Mitigating Bias in Vision-Language Model from a Causal Mediation Perspective
- "You Gotta be a Doctor, Lin": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations
- [Sep 21, 2024] I'm giving a talk at Human-Center AI conference. Thanks for the invitation!
- [Sep 2024] Congrats for the collaborators for the acceptance at EMNLP! See everyone there!
- [Aug 2024] Xiaoyuan Yi and I gave a tutorial on LLM Alignment at IJCAI 2024! The slides can be accessed here.
Talks
- Tutorial: AI Meets Values: History, Essence, and Recent Advances of Big Model's Value Alignment. IJCAI 2024.
- Tutorial: Trustworthy and Responsible AI. AAAI 2023.
- Detect and mitigate bias in NLP. AKBC KG-BIAS work shop, 2020.
Education / Experience
- Postdoc, University of Maryland, College Park. 2022.01 - 2023.06
- Ph.D., University of California, Los Angeles. 2017.9 - 2021.12
- Google Research Intern, NYC. 2021.06 - 2021.09
- AI2 Research Intern, Seattle. 2020.09 - 2020.12
- Microsoft Research Intern, Redmond. 2020.06 - 2020.09
- Microsoft Research Intern, Redmond. 2019.06 - 2019.09
Awards (selected)
- SAC Highlight Paper Award, EMNLP, 2025
- 100 Brilliant Women in AI Ethics, 2025
- Capital One Research Award, 2024
- EMNLP Outstanding AC Award, 2024
- USC WiSE Gabilan Professorship, 2023
- NSF CI Fellowship, 2021
- MIT EECS Rising Star, 2021
- Microsoft PhD Fellowship, 2020
- SoCalNLP Symposium Best Poster Award, 2018
- UCLA Graduate Division Fellowships, 2017
- EMNLP 2017 Best Long Paper Award, 2017
- Outstanding Graduate of Beijing City, 2016