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.

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/...

Hongli Zhan@hongli-zhan.bsky.social · 3mo ago

New paper! 🏁 Last one from my PhD at UT Austin. LLMs sound empathic but repeat the same discourse moves turn after turn — at 2x the rate of humans. We built MINT🌿, the first RL framework for discourse move diversity in empathic dialogue. +25% empathy, −26% repetition. 📄 arxiv.org/abs/2604.11742

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

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...

arxiv.org

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)

✨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

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

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

I'll be presenting our work soon today from 11:15 to 11:30 AM @ Flagler. Come say hi!

Jessy Li@jessyjli.bsky.social · 2y ago

Wednesday at #EMNLP: @yatingwu.bsky.social will present our work connecting curiosity and questions in discourse. We built strong models to predict salience, outperforming large LLMs. 👉[Oral] Discourse+Phonology+Syntax2 10:30-12:00 @ Flagler also w/ Ritika Mangla @gregdnlp.bsky.social Alex Dimakis

@jessyjli.bsky.social and @kmahowald.bsky.social are awesome advisors! Please apply to join the team!

Jessy Li@jessyjli.bsky.social · 3y ago

Echoing @kmahowald.bsky.social! We are a super interdisciplinary comp ling group at UT Linguistics, collaborating across campus with CS, ECE, Psych, the iSchool, and more. Join us & apply by Dec 1!

Looking forward to talking about this work and more at UT Austin this Friday.

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

I'm happy to announce that 🐮Lil-Bevo🤠 is ready to see the world. It's UT Austin's submission to BabyLM with @kmahowald.bsky.social Juan Diego & Kaj Bostrom. We tried 3 strategies inspired by human learning - music, shorter sequences, and targeted pretraining. Read our paper: arxiv.org/abs/2310.17591

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

📢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