iiinova — where your digital self keeps evolving

Yong Zheng-Xin (Yong)

@yongzx.bsky.social

66 followers 80 following 14 posts

ml research at Brown University // collab at Meta AI and Cohere For AI 🔗 yongzx.github.io

Posts Replies Media

Reposted by Yong Zheng-Xin (Yong)

Cohere Labs @cohereforai.bsky.social · 03/06/2025

It’s been two years since cross-lingual jailbreaks were first discovered. How far has the multilingual LLM safety research field advanced? 🤔 📏 Our comprehensive survey reveals that there is still a long way to go.

153

Reposted by Yong Zheng-Xin (Yong)

Julia Kreutzer @juliakreutzer.bsky.social · 04/06/2025

🚨LLM safety research needs to be at least as multilingual as our models. What's the current stage and how to progress from here? This work led by @yongzx.bsky.social has answers! 👇

042

Reposted by Yong Zheng-Xin (Yong)

faridlazuarda.bsky.social @faridlazuarda.bsky.social · 10/05/2025

Can English-finetuned LLMs reason in other languages? Short Answer: Yes, thanks to “quote-and-think” + test-time scaling. You can even force them to reason in a target language! But: 🌐 Low-resource langs & non-STEM topics still tough. New paper: arxiv.org/abs/2505.05408

arxiv.org

Crosslingual Reasoning through Test-Time Scaling

Reasoning capabilities of large language models are primarily studied for English, even when pretrained models are multilingual. In this work, we investigate to what extent English reasoning finetunin...

121

Reposted by Yong Zheng-Xin (Yong)

Julia Kreutzer @juliakreutzer.bsky.social · 09/05/2025

Multilingual 🤝reasoning 🤝 test-time scaling 🔥🔥🔥 New preprint! @yongzx.bsky.social has all the details 👇

051

Yong Zheng-Xin (Yong) @yongzx.bsky.social · 09/05/2025

📣 New paper! We observe that reasoning language models finetuned only on English data are capable of zero-shot cross-lingual reasoning through a "quote-and-think" pattern. However, this does not mean they reason the same way across all languages or in new domains. [1/N]

2123