RT @xinyue_cui411: Can we create effective watermarks for LLM training data that survive every stage in real-world LLM development lifecycl….

RT @johntzwei: Hi all, after a month in hiding in Vienna, I will be attending #ACL2025! Please reach out if you are interested in chatting….

RT @yanaiela: I'll be at #ACL2025 next week!.Catch me at the poster sessions, eating sachertorte, schnitzel and speaking about distribution….

I’ll be at ACL 2025 next week where my group has papers on evaluating evaluation metrics, watermarking training data, and mechanistic interpretability. I’ll also be co-organizing the first Workshop on LLM Memorization @l2m2_workshop on Friday. Hope to see lots of folks there!.

RT @qinyuan_ye: 1+1=3.2+2=5.3+3=?. Many language models (e.g., Llama 3 8B, Mistral v0.1 7B) will answer 7. But why?. We dig into the model….

RT @johntzwei: Hi all, I'm going to @FAccTConference in Athens this week to present my paper on copyright and LLM memorization. Please reac….

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? @yyqcode dives deep to show that faulty model internal beliefs (representations of “truthfulness”) drive retraction failures!.

RT @yyqcode: 🧐When do LLMs admit their mistakes when they should know better?. In our new paper, we define this behavior as retraction: the….

RT @DeqingFu: posted my slides for today's talk here:. check it out!.

RT @DeqingFu: Textual steering vectors can improve visual understanding in multimodal LLMs!. You can extract steering vectors via any inter….

RT @stanfordnlp: For this week’s NLP Seminar, we are thrilled to host @DeqingFu to talk about Closing the Modality Gap: Benchmarking and Im….

RT @l2m2_workshop: 📢 @aclmeeting notifications have been sent out, making this the perfect time to finalize your commitment. Don't miss the….

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).

RT @VeredShwartz: I've noticed (& confirmed with multiple people at #naacl2025) that NLP _for_ humans is more popular than ever while NLP _….

Check out @BillJohn1235813 ‘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.

RT @BillJohn1235813: At @naaclmeeting this week! I’ll be presenting our work on LLM domain induction with @_jessethomason_ on Thu (5/1) at….

RT @DeqingFu: I’ll be at @naaclmeeting this week. Excited to meet old and new friends!.

Really proud of this interdisciplinary LLM evaluation effort led by @BillJohn1235813 . 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!.

RT @BillJohn1235813: 🚨 New work!.LLMs often sound helpful—but fail to challenge dangerous medical misconceptions in real patient questions.….

RT @l2m2_workshop: Hi all, reminder that our direct submission deadline is April 15th! We are co-located at ACL'25 and you can submit archi….