Assistant professor @IllinoisCS, prev @allen_ai and @uwcse. HCI NLP. Designing language for different people.
Joined August 2016
- Tweets 137
- Following 312
- Followers 695
- Likes 205
7 Photos and videos
Such a fun project to work on with Lechen and Jiarui! TLDR: personalization is harder than most benchmarks indicate, mostly because people are people and models are not people. Check out Lechen's post and paper for more!
1/ When chatbots remember something about you in “personalized” answers, does it ever feel uncomfortable, offensive, or just unnecessary?
🚨 Our paper argues these misalignments reflects a deeper issue in personalization: over-reliance on synthetic users and LLM judges.
🧵👇
1
10
392
Apr 6
The STAR workshop at #CHI2026 is just over a week away! Due to increased interest, we're capping open-door attendance at 100. To make sure everyone interested has a spot, please sign up below.
📝Register: forms.gle/YCnP7QnWeuvZNvCN9
🌐 Details: chi-star-workshop.github.io
ALT A banner for the STAR (science and technology of augmented reading) workshop with a lower tag line of "What does the future hold for how we read?"
1
6
623
Feb 3
Deadline for submission in just under 10 days! Reach out if you have any questions.
19 Dec 2025
What is future of reading? 📗
Announcing the 1st Science & Technology of Augmented Reading (STAR) workshop at #CHI2026!
We want your takes on: 🤖 AI & Agents for reading 👁️ Visual Interactions 🗺️ Domains (Code, Law, Ed, etc.)
👇 Submit a 2-4 pg paper: chi-star-workshop.github.io/
1
2
8
540
Tal August retweeted
Jan 19
Internship opportunity! Please share!
📣 I'm looking to hire an intern in human-centered NLP for the agents team @togethercompute. Come work on frontier AI systems that tackle complex agentic tasks!
Research direction is open and looking to publish in NLP and HCI venues
21
64
585
43,878
Tal August retweeted
Jan 8
Current long-term conversation benchmarks focus on recall.
But this ignores key skills like recognizing what user information is valuable & leveraging it to improve future interactions.
To address this gap, we present MultiSessionCollab to evaluate agents in a multi-session collaboration environment.
3
13
29
3,734
19 Dec 2025
What is future of reading? 📗
Announcing the 1st Science & Technology of Augmented Reading (STAR) workshop at #CHI2026!
We want your takes on: 🤖 AI & Agents for reading 👁️ Visual Interactions 🗺️ Domains (Code, Law, Ed, etc.)
👇 Submit a 2-4 pg paper: chi-star-workshop.github.io/
5
13
1,941
18 Oct 2025
Go work with Lucy, she’s great!
PhD apps season is here! 😱🥳
Apply to do a PhD @WisconsinCS (as pictured) w/ me to research:
- Societal impact of AI
- NLP ←→ CSS and cultural analytics
- Computational sociolinguistics
- Human-AI interaction
- Culturally competent and inclusive NLP
lucy3.github.io/prospective-…
ALT 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.
ALT 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.
ALT A bicolor white cat with seal-colored markings, looking upwards with big wide dark eyes.
10
3,567
30 Jul 2025
I'm unfortunately not at #ACL2025 and so missed @priyanka_karg's presentation on tree-structured debates for comparative reasoning. Go talk to her about automating scientific discovery!
Paper: arxiv.org/abs/2502.14767 w/
@wonderingishika
@dmguiuc
youtube.com/watch?v=HlMVvHnM…
1
13
1,224
11 Jun 2025
🚨Calling all writing tutors & instructors!
Can writing tools give guidance, but not text suggestions?
We built a prototype based on conversations with tutors, and would love your thoughts:
📝 Try it out tinyurl.com/writor-system
🧾 Take a short survey to enter a $20 raffle
6
10
1,310
🖋️ Curious how writing differs across (research) cultures?
🚩 Tired of “cultural” evals that don't consult people?
We engaged with researchers to identify & measure ✨cultural norms✨in scientific writing, and show that❗LLMs flatten them❗
📜 arxiv.org/abs/2506.00784
1/11
ALT An overview of the work “Research Borderlands: Analysing Writing Across Research Cultures” by Shaily Bhatt, Tal August, and Maria Antoniak. The overview describes that We survey and interview interdisciplinary researchers (§3) to develop a framework of writing norms that vary across research cultures (§4) and operationalise them using computational metrics (§5). We then use this evaluation suite for two large-scale quantitative analyses: (a) surfacing variations in writing across 11 communities (§6); (b) evaluating the cultural competence of LLMs when adapting writing from one community to another (§7).
4
18
93
10,972
Can AI really help with literature reviews? 🧐
Meet Ai2 ScholarQA, an experimental solution that allows you to ask questions that require multiple scientific papers to answer. It gives more in-depth, detailed, and contextual answers with table comparisons, expandable sections for subtopics, and citations with paper excerpts for verification 💡
Try Ai2 ScholarQA now: scholarqa.allen.ai
More in 🧵
ALT Ai2 ScholarQA logo
14
70
219
41,549
11 Nov 2024
Excited to be at #EMNLP2024 this week! Would love to talk about:
🥼NLP for science, health, and legal text
📚Augmented reading and writing
🔀Human - AI interactions
Also any food recs are greatly appreciated.
1
41
3,293
11 Nov 2024
I will also be recruiting ~1 PhD student this year at UIUC. If you are interested in the above topics and applying to PhD programs, let’s talk!
2
1
511
Tal August retweeted
6 Nov 2024
* interrupting your election doomscrolling *
I'm on the job market! I address online abuse as the next frontier of security & privacy, so all people using tech feel safe. Open to TT faculty/industry research roles in the US/abroad -- lmk if you know of a good home for my work!
3
32
99
13,835
Hi friends, colleagues, followers.
I am on the faculty job market! I am a PhD student @BerkeleyISchool @berkeley_ai. I work on NLP, and I believe all language, whether AI- or human-generated, is ✨social and cultural data✨. My work includes: 🧵
10
71
389
57,714
Tal August retweeted
16 Oct 2024
Check out our paper here: dl.acm.org/doi/abs/10.1145/3…
This work was done last summer with amazing collaborators at semantic scholar / ai2: @josephcc @tal_august @amyxzh @dsweld
And come chat with us during the “Learning to Learn” session at 3:35pm on Weds 10/16!
1
6
584
Excited to share that our paper on plain language summarization evaluation has been accepted to the #EMNLP2024 main conference! I’ll be in Miami and will have several PhD openings for Fall 2025. Feel free to reach out if you’d like to chat!
(1/n) Announcing 🍎APPLS, a testbed to evaluate metrics for plain language summarization!
arxiv.org/abs/2305.14341
Joint work with @tal_august, @GondyLeroyUA, Trevor Cohen @UW BIME, and @lucyluwang #NLProc #SDProc
2
6
41
8,058
New paper 📝 @allen_ai! We worked with educators to identify a novel angle for evaluating language models' reasoning around math and pedagogy. 👩🏻🏫 🐟🍏
We ask, can LMs discern which skills and concepts are targeted by math content?
Preprint: arxiv.org/abs/2408.04226
ALT An example of a math problem involving operations in base ten in our dataset, along with standards it does and doesn't align with. This figure illustrates two task formats: verification and tagging.
7
16
134
24,882
Tal August retweeted
11 Aug 2024
Presenting this legal storytelling work in the poster session starting at 11:00AM on August 12 (Monday). Come to chat with me!
22 Mar 2024
Can LLMs promote #learning and #teaching?
Our latest work combines #LLMs and #storytelling, a widely-used ancient technique in education, to facilitate the learning of legal concepts and bridge the knowledge gaps between experts and non-experts.
arXiv: arxiv.org/abs/2402.17019
2
36
3,423
Tal August retweeted
27 Jun 2024
Interdisciplinary researchers, please take our survey!
▶️ forms.gle/XULo3xTbkm9nuSWDA
Just 6 questions, should take just 2-3 minutes, and we would be so grateful for your input 🙏
Calling digital humanists, computational social scientists, and anyone moving between communities!
📜 𝑊ℎ𝑎𝑡 𝑚𝑎𝑘𝑒𝑠 𝑎𝑛 𝐴𝐶𝐿 𝑝𝑎𝑝𝑒𝑟, 𝑎𝑛 𝐴𝐶𝐿 𝑝𝑎𝑝𝑒𝑟?
We want to study writing across research communities. If you submit to different venues, do interdisciplinary research, or collaborate across disciplines, please fill out our survey:
forms.gle/XULo3xTbkm9nuSWDA
8
27
4,978