🚨DEADLINE EXTENSION🚨We extended the submission deadline to *JUNE 22*. The technical report deadline has also been extended to June 29. Come submit your exciting results! Submit Here: SciCap.AI

The SciCap Challenge (SciCap.AI) organizers & *the winning teams* will present their cool work at #IJCAI2024 IJCAIconf. See you all at Jeju! And yes, we have new stickers :) (Deleted & reposted to fix #IJCAI2025 time-machined tag 🙃

Happy Friday! We're looking for a few more participants to use our LLM-powered data annotation tools for a week or two. We will pay $50! Please sign up here: forms.gle/dizBG4boxViCPG…

[Please RT📢] SEA Lab (sea-lab.space) is hiring 1 postdoc in Spring/Fall'25 and 1-2 PhD in Fall'25! We build next-gen #HCI and #HAI techniques for health & medical applications. Visit JOIN US page for more details. FAQs are highly recommended to read before applying.

The PSU Crowd AI Lab gang at #COLM2024 Conference on Language Modeling

At #UIST2024, many of you have met Sam Ho Yin (Sam) Ng, an MS student from PSU Crowd AI Lab, who is friendly, curious, and active. I want to tell you something he's too humble to tell you: He published a short IEEE VIS paper with Steven He and me! arXiv: arxiv.org/abs/2408.06494

I doubt about what I have learnt from GPT-4o over the past few hours🤔

TODAY at 2pm in the Resource and Evaluation 3 session in Flagler (Lower Level) Ruyuan Wan will give an oral presentation about this. See you soon! #EMNLP2024

We PSU Crowd AI Lab and friends had a great time at #EMNLP2024. See you all next time!

🚨 Have experience *using LLMs to label data*? We want to hear from you! We’re studying how LLMs are integrated into annotation workflows. 🕒 10–20 mins 🎁 Chance to win 1 of 3 $20 Amazon gift cards! 📋 Take the survey: forms.gle/5H7BT4jGUK3LQ7… #AI #LLM #DataAnnotation

We PSU Crowd AI Lab are curious about how people use LLM to *label data*. Please take a few minutes to fill out our short survey! #NLProc #LLM #Data #HCI Find our survey here: forms.gle/5H7BT4jGUK3LQ7… (IRB approved; led by Steven He)

Our small and cool paper on benchmarking NLP models across *language varieties* (CN/TW Mandarin) got in #NAACL2025 main. Our long and solid SciCap Challenge evaluation paper got in TACL. Big congrats to Edward Hsu and Zixin Tang ✈️IJCAI Guangzhou from PSU Crowd AI Lab. Both are tough fights.

In this era of vibe coding fueled by LLMs, our #CHI2025 paper, led by amazing Steven He, asked a simple question: Can we really get away with *not* using gold labels? Paper: arxiv.org/abs/2502.11267 1/n

AND this amazing Zeyu (Steven) He Steven He passed his proposal for thesis yesterday :) Happy advisor week!

We PSU Crowd AI Lab are at #CHI2025! We will present papers of 小紅書 RedNote #寶寶輔食, Prompting in the Dark, Crowd+LLM creative writing (INSPO), and more :) Come say hi!

I will present our #CHI2025 paper, Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent (dl.acm.org/doi/10.1145/37…). 📅 Wednesday, April 30 ⏲️ 9:00 AM – 9:12 AM 📍 G401 We would love for you to stop by!

I guess no one really like a 9am remote presentation on Day 3 of #CHI2025, but Steven He will try to prove me wrong--Prompting in the Dark at 9am in G401 TODAY! I will be there in person; happy to chat!

Happening now in G401! #CHI2025

I’m at NACCL and happy to chat!

We PSU Crowd AI Lab are looking for *native speakers* of English or Spanish for our study. It's a remote study in which you review+label 200 reviews. We pay $20. Sign up here: forms.gle/DKkmhSBQh5NUd7… Zixin Tang ([email protected]) is happy to answer any questions!