Check our latest cultural survey paper presented in the #EMNLP2024 last week!
with Prof. Monojit and @sagnikmukherjee.bsky.social
📣 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]
Really enjoyed working on this project. Kudos to the team that makes this possible! 🙌
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
first skeet!
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...
📣 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]
🚨 Paper Alert: “RL Finetunes Small Subnetworks in Large Language Models”
From DeepSeek V3 Base to DeepSeek R1 Zero, a whopping 86% of parameters were NOT updated during RL training 😮😮
And this isn’t a one-off. The pattern holds across RL algorithms and models.
🧵A Deep Dive
📢📢LLMs are biased towards Western Culture. Well, okay, but what do you mean by "Culture"?
In our survey of on cultural bias in LLMs, we reviewed ~90 papers. Interestingly, none of these papers define "culture" explicitly. They use “proxies”. [1/7]
[Appeared in EMNLP mains]
