📢#ACL2025 is inviting nominations and self-nominations to the ACL 2025 programme committee (reviewers or area chair) ➡️ forms.gle/Yu34Z13YzQ3sM8… deadline for nominations 🗓️ 16 Dec 2024. 🙏

Let features speak!😎 Excited to share our latest work: Verbalized Representation Learning!🚀 We let AI to describe visual features in its own words, mimicking "human engineering." Using a vision-language model, it generates and implements features described in language! ✨

🌍Are LLMs aware of cultural and legal safety in today’s geo-diverse world? 🚀Introducing SafeWorld, our #NeurIPS2024 paper and benchmark assessing LLMs’ understanding of geo-diverse safety, based on cultural norms and policies across 50 countries and 493 regions/races. ⚖️We

A behavior is safe in country A, but may be unsafe in country B. Check out our #NeurIPS2024 SafeWorld! It evaluates how well LLMs could provide appropriate and precise responses under the scenarios involving geo-diverse cultural and legal safety! arxiv.org/abs/2412.06483

Ctrl-G helps with writing #NeurIPS2024 announcements! Interactive text editing tool based on Ctrl-G released at billkunghappy.github.io/Ctrl-G/ Po-Nien Kung

Can an LLM agent be a data scientist? Check out our paper and chat with Xueqing Wu at NeurIPS

🎉🎉🎉 Congratulations to new #NAACL board members: Steven Bethard Steven Bethard (Treasurer) Nanyun (Violet) Peng Violet Peng Helena Gómez-Adorno HelenPy naacl.org/posts/2024-12-… Thank you all for voting!

congrats Violet Peng! Thanks for your service

We will host the 5th Workshop on TrustworthyNLP at NAACL 2025! We welcome both archival and non-archival submissions. See CFP for details.

Introducing Self-Routing RAG, a framework that equips selective retrieval with the ability to (1) route between multiple knowledge sources and (2) fully leverage the parametric knowledge of the LLM itself. Paper: arxiv.org/abs/2504.01018 (1/N)

🚨 New NLP seminar series alert! 🚨 Check out UCLA NLP Seminar series featuring cutting-edge talks from top researchers in NLP and related areas. Great lineup, timely topics, and open to all (zoom)! 🧠💬 📅 Schedule + details: uclanlp.github.io/nlp-seminar/

📣 For this week’s NLP Seminar, we are thrilled to host Zhe Gan Zhe Gan to give a talk titled “How to Build Your Multimodal LLMs: From Pre-training to Post-training and Agents”! 🗓️ 4/11 Fri 2pm PT Registration: forms.gle/TNXfBZJiMJjL18…

For this week’s NLP Seminar, we are thrilled to host David Bamman David Bamman to give a talk titled Measuring Representation and Linguistic Variation in Hollywood! 🗓️ 4/18 Fri 2pm PT Registration: forms.gle/hge16zkv3YnzvR…

Excited to share my first project at UCLA! We built MOSAIC — a social network simulator where LLM-powered agents behave like real users on social media. They post, share, flag, and debate the factuality of news content — all at scale. It’s open-source. 🧵 TL;DR 🌐 Realistic

Excited to speak more about AI creativity at SSNLP today in Singapore ssnlp-website.github.io/ssnlp25/ Also look forward to hear what Qwen team has to say about their latest breakthrough! Friends in Singapore: let’s catch up!

For this week’s NLP Seminar, we are thrilled to host Aditya Kusupati Aditya Kusupati to give a talk titled Matryoshka Principles for Adaptive Intelligence! When: 5/9 Fri 2pm PT Registration: forms.gle/j3LNvNbdfnu1xL…

Humans are capable of providing preferences in similar, but non-identical contexts! So why restrict LLMs? In our #ACL2025 Findings paper, we propose Joint Preference Optimization 📷, a novel objective for aligning LLMs that optimizes preferences over joint instruction-response

For this week’s NLP Seminar, we are thrilled to host Emma Pierson  Emma Pierson to give a talk titled Using New Data to Answer Old Questions! When: 5/16 Fri 2pm PT Registration: forms.gle/9sNYv2isfcqYQC…

🚨 New work: LLMs still struggle at Event Detection due to poor long-context reasoning and inability to follow task constraints, causing precision and recall errors. We introduce DiCoRe — a lightweight 3-stage Divergent-Convergent reasoning framework to fix this.🧵📷 (1/N)