When/where do we listen?!
07.03.2026 01:34
👍 1
🔁 0
💬 1
📌 0
When/where do we listen?!
We wrote this paper partly for this reason! github.com/bamman-group...
Read about @guhrs.bsky.social:
www.ischool.berkeley.edu/news/2026/po...
Title, author list, and two figures from the paper. Title: The Aftermath of DrawEduMath: Vision Language Models Underperform with Struggling Students and Misdiagnose Errors Authors: Li Lucy, Albert Zhang, Nathan Anderson, Ryan Knight, Kyle Lo Figure 1: On the left is a math problem, where students are asked to draw x < 5/2 on a number line. The right side shows two example student responses that differ in correctness. DrawEduMath pairs each math problem with one student response, and prompts VLMs to answer questions about the student response. Figure 2: VLMs consistently perform worse on answering DrawEduMath benchmark questions pertaining to erroneous student responses. Performance on non-erroneous student responses is labeled with specific VLMs’ names; that same model’s performance on erroneous student responses is directly below.
Models are now expert math solvers, and so AI for math education is receiving increasing attention.
Our new preprint evaluates 11 VLMs on our QA benchmark, DrawEduMath. We highlight a startling gap: models perform less well on inputs from K-12 students who need more help. 🧵
Just a testimonial: potato 1.0 is amazing and I use it all the time for annotation. Excited to see what’s in 2.0!
New paper to appear at EACL 2026 main conference, and it's now up on arxiv: arxiv.org/pdf/2505.17536. The character limit here is insane, so I'll let the screenshots speak for themselves. We put together a new dataset for conversational role attribution & thread disentanglement.
Calling out the papers by name in the appendix is noteworthy. Obvs mistakes happen (as the authors note in their choice to report it) but it’s a useful caution that highlights the stakes: you don’t want to end up in an appendix like this
That DHS/ICE and anyone up or down the chain could describe this murder victim as a “domestic terrorist” is utter depravity.
This is such a great post — and “rituals” (describing some conventions of a community around knowledge production, like publication checklists) is le mot juste
I used to be astonished that John Keats wrote everything by 26yo (and still am) but now newly in awe to learn that late Beatles (“let it be” etc) were 29?!
And for my own research corner, I’d definitely encourage those working in computational social science/cultural analytics to consider it.
This program brought together such a wonderful group of ~30 PhD students for two weeks at Berkeley last year with backgrounds in sociology, information, law, computer science and more — same idea but in Oxford next summer; apply by Feb 2 if you’re looking to make connections across fields
📢 Ph.D. STUDENTS: The app is now open to join us for the Oxford-Berkeley Summer Doctoral Program, an opportunity for students to learn from & engage with leading academics in the field of information and internet studies! #AcademicSky
Deadline ⏰: 2/2
#OIISDP #OIIBerkeleySDP
https://bit.ly/4p4CK2n
Congrats Oleg!!
The research would not exist without you!
@francescom.bsky.social you’re one of these friends I was thinking about!
Which had me look up that song in my Shazam history (yes I had to Shazam it), and sure enough it was there — the only time I’ve been able to pinpoint the exact moment a research idea took shape (1:38pm on 7/14/23)
Berkeley wrote up our work on measuring the stories in contemporary songs and had me reflect on the origin of that work in Bruce Springsteen’s “Thunder Road”
I’ve been to 3 now and I think it keeps getting better — next year Manchester early Jan!
While we might expect the singer-songwriters of the 1960s to be a high-water mark for narrativity, we find the opposite: narrativity has been steadily increasing, largely due to the rise of the strongly narrative genres of hip hop and rap.
Excited to get this work out in the world at #chr2025 (with Sabrina Baur, Mackenzie Cramer, Anna Ho and Tom McEnaney) -- asking: how much do contemporary songs tell stories, and how has that changed over the past half century?
anthology.ach.org/volumes/vol0...
New grant program announcement: You've heard me talk this morning about those 23 new DH awards from @schmidtsciences.bsky.social HAVI program? Well, we just announced our new RFP for 2026! Teams can be global too! Please consider applying. RFP here: www.schmidtsciences.org/opportunity/...
This talk made me want to connect these findings to those of @heuser.bsky.social @mellymeldubs.bsky.social et al. -- do LLM translations of Homer (i.e., poetry) sound like Lattimore or are they just in iambic pentameter (like Lattimore I think but unlike Wilson, who is more free verse).
En route to #CHR2025 in Luxembourg — looking forward to seeing people there!
📢 The #CHR2025 proceedings are out!
97 papers, ~1600 pages of computational humanities 🔥 Now published via the new Anthology of Computers and the Humanities, with DOIs for every paper.
🔗 anthology.ach.org/volumes/vol0...
And don’t forget: registration closes tomorrow (20 Nov)!
A staircase in the new School of Computer, Data & Information Sciences building at Wisconsin Madison. Tan wood structures surround tapestry art and a small indoor garden.
A view from above of the staircases in the Wisconsin CDIS building
An shot from below of winding wooden staircases and a glass atrium rooftop. The new School of Computer, Data & Information Sciences building at Wisconsin Madison.
A bicolor white cat with seal-colored markings, looking upwards with big wide dark eyes.
It's the season for PhD apps!! 🥧 🦃 ☃️ ❄️
Apply to Wisconsin CS to research
- Societal impact of AI
- NLP ←→ CSS and cultural analytics
- Computational sociolinguistics
- Human-AI interaction
- Culturally competent and inclusive NLP
with me!
lucy3.github.io/prospective-...
why intern at Ai2?
🐟interns own major parts of our model development, sometimes even leading whole projects
🐡we're committed to open science & actively help our interns publish their work
reach out if u wanna build open language models together 🤝
links 👇
The UC Berkeley School of Information is hiring an assistant professor in the broad field of Information--including areas of info seeking/retrieval, digital humanities, cultural analytics, info viz, & philosophy of information (among others). Deadline Nov 1! aprecruit.berkeley.edu/JPF05014
Trying to keep my professional chill but I’m SO excited Carnegie Mellon is launching a cluster hire in computational humanities—MULTIPLE JOBS!
1. Asst Teaching Track Prof in Computational Humanities - apply.interfolio.com/173622
2. Asst Tenure Track Prof in CH - apply.interfolio.com/173626
Unfortunately, I expect that the fact they won a pretty resounding fair use victory is going to be lost in much of the coverage. They lost on downloading & storing the LibGen dataset (straight infringement!), but the act of training on copyrighted material (+ making their own ebooks) was a win.