Serina Chang
@serinachang5.bsky.social
Incoming Assistant Professor at UC Berkeley in CS and Computational Precision Health. Postdoc at Microsoft Research, PhD in CS at Stanford. Research in AI, graphs, public health, and computational social science.
https://serinachang5.github.io/
https://serinachang5.github.io/
Blog post on exciting research happening at MSR, including our recent work ChatBench on human-AI vs AI-alone evaluation!
In this issue: our CHI 2025 & ICLR 2025 contributions, plus research on causal reasoning & LLMs; countering LLM jailbreak attacks; and how people use AI vs. AI-alone. Also, SVP of Microsoft Health Jim Weinstein talks rural healthcare innovation: msft.it/6013SHuu1
April 25, 2025 at 12:05 AM
Blog post on exciting research happening at MSR, including our recent work ChatBench on human-AI vs AI-alone evaluation!
Looking forward to taking part in this CHI'25 panel organized by @angelhwang.bsky.social !!
📣 Calling all #CHI2025 attendees who work with human participants: Join our panel discussion on #LLM, #simulation, #syntheticdata, and the future of human subjects research on Apr 30 (Wed), 2:10 - 3:40 PM (JP Time)
Post your questions for panelists here: forms.gle/m2mXY3xFafAX...
Post your questions for panelists here: forms.gle/m2mXY3xFafAX...
April 22, 2025 at 6:55 PM
Looking forward to taking part in this CHI'25 panel organized by @angelhwang.bsky.social !!
1st post on bsky!
What happens when a static benchmark comes to life? ✨ Introducing ChatBench, a large-scale user study where we *converted* MMLU questions into thousands of user-AI conversations. Then, we trained a user simulator on ChatBench to generate user-AI outcomes on unseen questions. 1/ 🧵
What happens when a static benchmark comes to life? ✨ Introducing ChatBench, a large-scale user study where we *converted* MMLU questions into thousands of user-AI conversations. Then, we trained a user simulator on ChatBench to generate user-AI outcomes on unseen questions. 1/ 🧵
April 11, 2025 at 5:57 PM
1st post on bsky!
What happens when a static benchmark comes to life? ✨ Introducing ChatBench, a large-scale user study where we *converted* MMLU questions into thousands of user-AI conversations. Then, we trained a user simulator on ChatBench to generate user-AI outcomes on unseen questions. 1/ 🧵
What happens when a static benchmark comes to life? ✨ Introducing ChatBench, a large-scale user study where we *converted* MMLU questions into thousands of user-AI conversations. Then, we trained a user simulator on ChatBench to generate user-AI outcomes on unseen questions. 1/ 🧵
Reposted by Serina Chang
Check out ChatBench, our new paper+dataset. We turned AI benchmarks into user-AI chats and show that AI-alone evals often fail to predict how real humans perform with AI.
@serinachang5.bsky.social @ashtonanderson.bsky.social
serinachang5.github.io/assets/files...
huggingface.co/datasets/mic...
@serinachang5.bsky.social @ashtonanderson.bsky.social
serinachang5.github.io/assets/files...
huggingface.co/datasets/mic...
serinachang5.github.io
April 9, 2025 at 9:29 PM
Check out ChatBench, our new paper+dataset. We turned AI benchmarks into user-AI chats and show that AI-alone evals often fail to predict how real humans perform with AI.
@serinachang5.bsky.social @ashtonanderson.bsky.social
serinachang5.github.io/assets/files...
huggingface.co/datasets/mic...
@serinachang5.bsky.social @ashtonanderson.bsky.social
serinachang5.github.io/assets/files...
huggingface.co/datasets/mic...