I missed this one when it came out but I can tell that it is one of the most useful piece of research I’ve read in a while.
“GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models”
https://arxiv.org/html/2410.05229v1
“GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models”
https://arxiv.org/html/2410.05229v1
Comments
https://bsky.app/profile/aelouass.bsky.social/post/3lfu5mc6hvs2b