Why Large Language Models Fail at Tabular Prediction

(arxiv.org)

18 points | by sbulaev 3 hours ago ago

2 comments

  • ismailmaj 37 minutes ago

    Unsure if it's LLMs that fail at tabular data or its just that tree boosting are spectacular at that task.

  • cyanregiment an hour ago

    Just have 2 LLMs debate whether tabs or spaces are the superior choice