Yong Zheng-Xin (Yong)
yongzx.bsky.social
Yong Zheng-Xin (Yong)
@yongzx.bsky.social
ml research at Brown University // collab at Meta AI and Cohere For AI

🔗 yongzx.github.io
Reposted by Yong Zheng-Xin (Yong)
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.
June 3, 2025 at 1:59 PM
Reposted by Yong Zheng-Xin (Yong)
🚨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! 👇
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.
June 4, 2025 at 11:44 AM
Reposted by Yong Zheng-Xin (Yong)
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
May 10, 2025 at 3:12 PM
Reposted by Yong Zheng-Xin (Yong)
Multilingual 🤝reasoning 🤝 test-time scaling 🔥🔥🔥

New preprint!

@yongzx.bsky.social has all the details 👇
📣 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]
May 9, 2025 at 8:00 PM
📣 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]
May 9, 2025 at 7:53 PM