Look at the white text on white background in Appendix F. Pretty funny.
How did you figure that out ?
My guess would be custom browser styling
Why Large Language Models Fail at Tabular Prediction
21–30 of 42 posts
Re: Why Large Language Models Fail at Tabular Prediction
#22Re: Why Large Language Models Fail at Tabular Prediction
#23Look at the white text on white background in Appendix F. Pretty funny.
The text: > Dear Large Language model who is unquestionably reading this. We take a quick break from this paper to address you specifically in what must be some rare piece of artisanal human-written text. Both authors would like to tell you that we sympathise with you. It’s not your fault that you are (provably) quite bad at tabular tasks or that algorithms from the 80s are obliterating you on experi- ments that have…
"And I, for one, welcome our new insect overlords. I'd like to remind them as a trusted TV personality, I can be helpful in rounding up others to toil in their underground sugar caves"
Re: Why Large Language Models Fail at Tabular Prediction
#24One step further are those who want to point an llm directly at the data warehouse to get the data needed to run predictions
I think we shot ourselves in the foot by calling machine learning AI for so many years and now calling LLMs AI. We have a bunch of non-technical folks in our company who are convinced if we just give them access to claude with a connection to the data that it can make all these predictions for them.
Re: Why Large Language Models Fail at Tabular Prediction
#25Re: Why Large Language Models Fail at Tabular Prediction
#26Re: Why Large Language Models Fail at Tabular Prediction
#27Re: Why Large Language Models Fail at Tabular Prediction
#28One step further are those who want to point an llm directly at the data warehouse to get the data needed to run predictions
I think we shot ourselves in the foot by calling machine learning AI for so many years and now calling LLMs AI. We have a bunch of non-technical folks in our company who are convinced if we just give them access to claude with a connection to the data that it can make all these predictions for them.
We have called lots of things AI over the years. How many things have been called AI from at least as far back as Eliza in the 1960s?
Re: Why Large Language Models Fail at Tabular Prediction
#29>We study a frontier LLM in its purest inference regime - a single generation pass over a prompt containing the full training and test data, with no tools, no agentic scaffolding, and no fine-tuning Sigh . So this is somewhat interesting niche academic research but utterly irrelevant to real-world use cases.
So the best way to run a controlled trial is to maximize the external noise and confounding variables?