Sign in

Yating Wu

@yatingwu.bsky.social
268 followers 213 following 7 posts

ECE Ph.D. from UT Austin, advised by @jessyjli and @AlexGDimakis I am on the 2026-2027 academic and industry job markets. yatingwu.info

PostsRepliesMedia
Yating Wu @yatingwu.bsky.social · 07/05/2026
What does a scientific figure make you wonder? 📊 We introduce MQUD: multimodal Questions Under Discussion for scientific figures. With 1,250 author-annotated questions over 245 figures from 56 papers, MQUD asks what scientific question a figure raises in context.
141
Reposted by Yating Wu
Hongli Zhan @hongli-zhan.bsky.social · 03/05/2026
1k+ downloads each on the MINT empathy models since release 🔥 Encouraging to see the interest in our work! tl;dr: In multi-turn empathic dialogue, LLMs reuse the same discourse moves far more often than humans do; MINT uses RL to diversify them. Give it a try!👇 huggingface.co/hongli-zhan/...
062
Reposted by Yating Wu
Ramya Namuduri @ramyanamuduri.bsky.social · 21/04/2025
Check out our paper for more results and analysis! 📝 arxiv.org/abs/2504.09373 🐙 github.com/AlliteraryAl... This was a fun collaboration with @yatingwu.bsky.social @asher-zheng.bsky.social @manyawadhwa.bsky.social @gregdnlp.bsky.social @jessyjli.bsky.social
arxiv.org
QUDsim: Quantifying Discourse Similarities in LLM-Generated Text
As large language models become increasingly capable at various writing tasks, their weakness at generating unique and creative content becomes a major liability. Although LLMs have the ability to gen...
051
Reposted by Yating Wu
Jessy Li @jessyjli.bsky.social · 21/02/2025
Do you want to know what information LLMs prioritize in text synthesis tasks? Here's a short 🧵 about our new paper, led by Jan Trienes: an interpretable framework for salience analysis in LLMs. First of all, information salience is a fuzzy concept. So how can we even measure it? (1/6)
1156
Reposted by Yating Wu
Leonie Weissweiler @weissweiler.bsky.social · 20/02/2025
✨New paper✨ Linguistic evaluations of LLMs often implicitly assume that language is generated by symbolic rules. In a new position paper, @adelegoldberg.bsky.social, @kmahowald.bsky.social and I argue that languages are not Lego sets, and evaluations should reflect this! arxiv.org/pdf/2502.13195
16819
Reposted by Yating Wu
Atlas Wang @atlaswang.bsky.social · 22/11/2024
I did a starter pack of ML/AI people at @utaustin.bsky.social Please distribute and feel free to self nominate! go.bsky.app/QLQznZg
2278
Reposted by Yating Wu
Jessy Li @jessyjli.bsky.social · 19/11/2024
We at UT Linguistics are hiring for 🔥 2 faculty positions in Computational Linguistics! Assistant or Associate professors, deadline Dec 1. UT has a super vibrant comp ling & #nlp community!! Apply here 👉 apply.interfolio.com/158280
0126
Yating Wu @yatingwu.bsky.social · 13/11/2024
I'll be presenting our work soon today from 11:15 to 11:30 AM @ Flagler. Come say hi!
010
Yating Wu @yatingwu.bsky.social · 09/11/2023
@jessyjli.bsky.social and @kmahowald.bsky.social are awesome advisors! Please apply to join the team!
020
Reposted by Yating Wu
Aaron Steven White @aaronstevenwhite.io · 04/11/2023
Looking forward to talking about this work and more at UT Austin this Friday.
Abstract for a talk entitled "Complex Situation Representations".
031
Reposted by Yating Wu
Jessy Li @jessyjli.bsky.social · 01/11/2023
Psych theories suggest that how we judge a situation (*cognitive appraisal*) leads to diverse emotions. Our #EMNLP 2023 Findings paper tests LLMs' ability to assess and explain such appraisals -- big gap between open-source LLMs and GPT3.5. Paper arxiv.org/abs/2310.14389 w Hongli Zhan, Desmond Ong
012
Reposted by Yating Wu
Jessy Li @jessyjli.bsky.social · 26/10/2023
To appear EMNLP2023: simplifying text involves explaining and elaborating concepts. Using QUDs in a question generation -> answering pipeline leads to much better generation of such elaborations! arxiv.org/abs/2305.10387 w/ @yatingwu.bsky.social Will Sheffield @kmahowald.bsky.social
031
Reposted by Yating Wu
Jessy Li @jessyjli.bsky.social · 24/10/2023
📢Our EMNLP 2023 work on Questions Under Discussion (QUD)! We introduce QUDeval, the first benchmark for evaluating the generation of open-ended questions and QUD parsing using linguistic principles. Paper: arxiv.org/abs/2310.14520 w/ @yatingwu.bsky.social, Ritika Mangla, @gregdnlp.bsky.social
0155