We are so excited that Scholar Inbox is supporting ACL 2025 @aclmeeting with personalized conference programs this year for the first time! https://t.co/Q0ytGl6qiB Just 5 minutes onboard and you'll get personalised recommendation of each ACL sessions. Don't miss a beat again!

📢This year, #ACL2025NLP partners with Scholar Inbox 🤝 to provide customized conference programs based on personal research interests to attendees. 🧑‍💻 The personalized programs can be accessed from any mobile device or PC via web browser. 📱💻 https://t.co/H7LUITra6H 👌

Also, we will present our ACL Demo paper: Scholar Inbox: Personalized Paper Recommendations for Scientists at Hall 5X, 28th July, 11:00-12:30. Welcome to come by and have a chat with our team! @HaoyuHe212 @MarkusFlicke

Excited to join the IT:U summer school this year! Looking forward to learning, sharing, and connecting with amazing researchers! 😀

📣 Excited to share our #CVPR2025 Spotlight paper and my internship project @wayve_ai: SimLingo. A Vision-Language-Action (VLA) model that achieves state-of-the-art driving performance with language capabilities. Code: https://t.co/hGMsXGAxPS Paper: https://t.co/cx0QCKMl3z

📣 Excited about our Cross Cultural Considerations in NLP workshop! @c3_nlp @ @naaclmeeting coming up in no time—just two weeks to go! Full program here: https://t.co/YZK3EcaU1W Co-org. w/ @sunipa17 @LucianaBenotti @daniel_hers @vinodkpg @YongCaoPlus @LiZhou21 @IfeAdebara ❤️

For more analysis and details, check out our paper: https://t.co/fbzEbONHbT Our code is available here:

🔍 Findings: Testing on three model families & seven models, our method consistently outperforms other approaches —even on unseen questions, countries, and an entirely new survey. While challenges still remain, we demonstrate the benefits of specialization for simulation.🚀

📂 Dataset: We construct the simulation dataset from the World Values Survey (WVS) in both English & Chinese. To test generalization, we use a subset of GlobalOpinionQA, specifically the Pew Global Attitudes Survey.

🛠 Method: We introduce a fine-tuning approach that uses first-token probabilities to align predicted and actual survey response distributions. By optimizing with KL divergence loss, our method effectively minimizes divergence from real-world survey data. 📊

💡Motivation: Large-scale surveys are crucial for social science, but they’re expensive and time-consuming. What if LLMs could simulate group-level survey results? Thus, we try to specialize LLMs for simulating this task, using country-level data from cultural surveys. 🌍

🎉 Excited to share our NAACL main paper on simulating survey response distributions via first-token alignment fine-tuning. Many thanks to our collaborators: Haijiang Liu, @rnav_arora @IAugenstein @paul_rottger and @daniel_hers. More details, paper link and code, see below👇

Transforming Science with LLMs A comprehensive survey on AI-assisted scientific discovery, experimentation, content generation, and evaluation.

Very interesting work that comprehensively investigates cultural knowledge in LLMs in the domain of food! Looking forward to more discussion at NAACL.

📣 Second Call for Papers! 🎉 We’re extending our CFP to February 6, 2025 ⏳—more time to submit your work on culture, society & NLP! 📅 New Deadline: Feb 6, 2025 🔗 Workshop details: https://t.co/iSYTYMh5N1 Submit now & join us! 📝✨ #NLP #C3NLP #CulturalNLP #NAACL2025

It's hugely disappointing to hear such arguments from a top AI conference. 😡More efforts are needed to avoid LLMs aligning with these offensive points. (Sometimes LLMs behave more polite and respectful so far...)

Looking forward to discussing fascinating cultural research and meeting again next May! 😊 Please check for our CFP details if you are interested!🗓️

Thrilled to have participated in such an insightful workshop! A fantastic opportunity to meet, brainstorm, and engage in discussions with brilliant minds.

Recent work led by @constanzafierro and @negarforoutan on understanding the mechanisms behind multilingual factual recall

Amazing brochure to #ACL2024 🇹🇭 with an amazing 2nd edition of the workshop @c3_nlp 🗺️ with amazing co-organizers ♥️