Join us as a student volunteer at #NAACL2015 ! aclweb.org/portal/content…

Billion-parameter LLMs still struggle with simple arithmetic? 📞 FoNE (Fourier Number Embedding) tackles this problem. By mapping numbers directly into Fourier space, it bypasses tokenization and significantly improves numerical accuracy with better efficiency and accuracy.

Many works addressing copyright for LLMs focus on model outputs and their similarity to copyrighted training data, but few focus on how the model was trained. We analyze LLM memorization w.r.t. their training decisions and theorize on its use in court arxiv.org/abs/2502.16290

When answering queries with multiple answers (e.g., listing cities of a country), how do LMs simultaneously recall knowledge and avoid repeating themselves? 🚀 Excited to share our latest work with Robin Jia! We uncover a promote-then-suppress mechanism: LMs first recall all

🎉Congrats to Aryan Gulati & Ryan Wang for receiving Honorable Mentions for the CRA Outstanding Undergraduate Researcher Awards! Aryan, a former CAIS++ co-president, was mentored by CAIS Associate Director Swabha Swayamdipta. Ryan worked with CAIS faculty Robin Jia. viterbischool.usc.edu/news/2025/03/f…

Hi all, reminder that our direct submission deadline is April 15th! We are co-located at ACL'25 and you can submit archival or non-archival. You can also submit work published elsewhere (non-archival) Hope to see your submission! sites.google.com/view/memorizat…

🚨 New work! LLMs often sound helpful—but fail to challenge dangerous medical misconceptions in real patient questions. We test how well LLMs handle false assumptions in oncology Q&A. 📝 Paper: arxiv.org/abs/2504.11373 🌐 Website: cancermyth.github.io 👇 [1/n]

Really proud of this interdisciplinary LLM evaluation effort led by Wang Bill Zhu . We teamed up with oncologists from USC Keck SOM to understand LLM failure modes on realistic patient questions. Key finding: LLMs consistently fail to correct patients’ misconceptions!

I’ll be at NAACL HLT 2025 this week. Excited to meet old and new friends!

At NAACL HLT 2025 this week! I’ll be presenting our work on LLM domain induction with Jesse Thomason on Thu (5/1) at 4pm in Hall 3, Section I. Would love to connect and chat about LLM planning, reasoning, AI4Science, multimodal stuff, or anything else. Feel free to DM!

Check out Wang Bill Zhu ‘s excellent work on combining LLMs with symbolic planners at NAACL on Thursday! I will also be at NAACL Friday-Sunday, looking forward to chatting about LLM memorization, interpretability, evaluation, and more

I've noticed (& confirmed with multiple people at #naacl2025) that NLP _for_ humans is more popular than ever while NLP _with_ humans (user studies, human eval, crowdsourcing) gets push back from reviewers who often don't consider this a valid contribution for *CL conferences 1/2

Becoming an expert requires first learning the basics of the field. Learning the basics requires doing exercises that AI can do. No amount of class redesign can change this. (What will change: the weight of exams in computing the final grade)

📢 ACL 2025 notifications have been sent out, making this the perfect time to finalize your commitment. Don't miss the opportunity to be part of the workshop! 🔗 Commit here: openreview.net/group?id=aclwe… 🗓️ Deadline: May 20, 2025 (AoE) #ACL2025 #NLProc

Textual steering vectors can improve visual understanding in multimodal LLMs! You can extract steering vectors via any interpretability toolkit you like -- SAEs, MeanShift, Probes -- and apply them to image or text tokens (or both) of Multimodal LLMs. And They Steer!

For this week’s NLP Seminar, we are thrilled to host Deqing Fu to talk about Closing the Modality Gap: Benchmarking and Improving Visual Understanding in Multimodal LLMs! When: 5/22 Thurs 11am PT Non-Stanford affiliates registration form (closed at 9am PT on the talk day):

posted my slides for today's talk here: deqingfu.github.io/_docs/20250522… check it out!

🧐When do LLMs admit their mistakes when they should know better? In our new paper, we define this behavior as retraction: the model indicates that its generated answer was wrong. LLMs can retract—but they rarely do.🤯 arxiv.org/abs/2505.16170 👇🧵

If an LLM’s hallucinated claim contradicts its own knowledge, it should be able to retract the claim. Yet, it often reaffirms the claim instead. Why? Yuqing Yang dives deep to show that faulty model internal beliefs (representations of “truthfulness”) drive retraction failures!

Hi all, I'm going to ACM FAccT in Athens this week to present my paper on copyright and LLM memorization. Please reach out if you are interested to chat about law, policy, and LLMs!