Serina Chang

@serinachang5

Assistant prof @UCBerkeley, EECS & CPH | postdoc @MSFTResearch | CS PhD @stanford | Human-centered AI, graphs/networks, public health & social science

serinachang5.github.io

Joined December 2016

461 Following

4,146 Followers

Replies Reposts Media

Pinned
Serina Chang
@serinachang5
Nov 20, 2025
📢 Come work with me at UC Berkeley @berkeley_ai! I’m recruiting PhD students in @Berkeley_EECS and @UCJointCPH. I work on AI for social good, simulating humans with AI, human-AI interaction, and applications in public health & social science. serinachang5.github.io
10
Serina Chang
@serinachang5
Oct 15
Congratulations, Bill!!! 🎉 So excited to have you here with us at Berkeley! 🐻
Wang Bill Zhu
@BillJohn1235813
Oct 15
A very overdue life update: came across my graduation photos and realized I never shared them! I finished my PhD at @CSatUSC ! 🎓 So grateful to my advisors @robinomial and @_jessethomason_ for all their guidance and support, and to my partner for being there through all the
Serina Chang
@serinachang5
Oct 7
📣 New paper, led by @JosephJSSuh ! Human-AI interaction datasets form a foundation for downstream research: as evidence of how people interact with AI and as training and validation for user models. But how solid are these foundations? 1/3
Joseph Suh
@JosephJSSuh
Oct 7
WildChat, LMSYS, ShareChat… each human-LLM chat dataset aims to capture "real-world" AI use. But do they paint the same picture? Not quite. From user messages alone, a classifier can name a chat's source dataset, and user models trained on them inherit these signatures 🧵👇
2
Serina Chang
@serinachang5
Sep 25
Excited to share that our paper on evaluating AI political neutrality (PARETO) has been accepted to #NeurIPS2026 E&D as a Spotlight!! 🎉 This is an active area of research for us and we're exploring several directions coming out of this work - get in touch if you're interested!
Serina Chang
@serinachang5
Jun 8
When people strongly disagree on an issue, can they agree on what makes a good AI response? We find: yes, more than you might expect! We present PARETO, a large human study w >200k evals, measuring the Pareto frontier of approval btwn opposing groups on controversial issues 🧵
1
Serina Chang
@serinachang5
Sep 15
New paper evaluating LLMs' professional knowledge across occupations! We develop a scalable approach to benchmarking occupation-specific knowledge by turning online authoritative sources into test questions. Really enjoyed working on this with @abhishekn and @ShreyasK1609!
Abhishek Nagaraj
@abhishekn
Sep 14
🚨🚨🚨 New paper alert 🚨🚨🚨 To understand LLMs impact on work, we first need to examine their capabilities across the entire occupation distribution. Doing this in a scalable way is hard and costly. Presenting - "ORQA: An Occupation-Realistic Question and Answer Framework

Serina Chang

Serina Chang’s posts