Excited to be in Thailand ☀️😎 🌺🥥 to attend #ACL2024! If you run into my PhD students from Georgia Tech NLP group - Yao Dou Yao Dou, Tarek Naous Tarek Naous, and Jonathan Zheng Jonathan Zheng, please say hi! 👋 Please also say hi to my other collaborators!

New research shows that Arabic and multilingual language models (LMs) exhibit bias toward Western culture – even in Arab cultural contexts. LMs trained on Wikipedia and web-crawls are the worst at adapting to Arab cultural contexts. Researchers conclude that the prevalence of

🏆 ACL Best Social Impact Paper Awards: - Having Beer after Prayer? Measuring Cultural Bias in Large Language Models by Naous et al. #NLProc #ACL2024NLP

Well done Tarek Naous! You can read about Tarek's impactful work here: cc.gatech.edu/news/llms-gene…

الحمدلله I'm honored to receive the Best Social Impact Paper Award at #ACL2024NLP for our work on cultural biases in LLMs! 🎖Paper: arxiv.org/abs/2305.14456 Together with Wei Xu Alan Ritter Michael Ryan

Couldn't have done it without the support and mentoring of my amazing advisor Wei Xu 💫

Happy to participate in the discussion on AI governance in Internet Governance at Georgia Tech 's annual workshop! #IGP2024

Wow give khamzat the title shot right now

There is a fake impersonator account that changed the number in my account from 207 to 206. DO NOT CLICK ANY LINKS FROM IT. Quanta DSPy is not a real thing. I am not a part of this. Working on reporting this.

❤️🌎 Introducing CARE: Multilingual Multicultural Human Preference Learning 3490 culturally relevant prompts + 31.7k Human/AI-written responses rated by multilingual speakers 💡 Key insights: - Even a small amount of cultural data improves popular LLMs consistently. - Deepseek-v3