Reasoning models are quite verbose in their thinking process. Is it any good? We find out that it enables reasoning models to be more accurate in telling what they know and don’t know (confidence)! Even non-reasoning models can do it better if they mimic the verbose reasoning! 👀

Been a pleasure to work on this project led by Hoyeon Chang and Jinho Park to study compositional generalization of LLMs in a systematic way, which is fundamentally connected to the latent multi-hop reasoning of LLMs that I've been investigating!

This work shows that it's possible to train a model to encode and predict latent sentence representations and successfully 👉close the gap with explicit reasoning using CoT👈! Huge kudos to Hyeonbin Hwang and byeongguk jeon who led this project. Had a lot of fun working with the team!

How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts? "We show that models are effective at identifying most unhelpful thoughts but struggle to recover from the same thoughts when these are injected into their thinking process, causing significant