Re:Do Large Language Models learn world models or just surfa...
by thaumasiotes on Sunday January 22, 2023 @02:25PM
(#34481308)
> I felt a bit crazy pushing back on this--surely, using more variables and more parameters will make the model fit historical data more closely, and a model which fits historical data more closely will fit future data more closely, and a model which fits future data more closely will be more useful?
> Explaining why this is wrong is really hard.
Seems straightforward. Points 1 and 3 are correct; point 2 is false.
Re:Do Large Language Models learn world models or just surfa...
by klodolph on Monday January 23, 2023 @02:48AM
(#34486465)
Points 1 and 2 are both wrong also.
Statistics is not intuitive.
Re:Do Large Language Models learn world models or just surfa...
by thaumasiotes on Monday January 23, 2023 @05:49AM
(#34487372)
Point 1 isn't wrong; it's correct. There's a reason the name for this problem is "overfitting".
Re:Do Large Language Models learn world models or just surfa...
by klodolph on Monday January 23, 2023 @01:02PM
(#34492486)
Yeah, it sounds like you’re assuming two things things here which are often (or usually) wrong:
1. No cross-validation, and
2. You have the ability to solve for additional parameters without losing accuracy.
Statistics is not intuitive.
I've only done a small amount of statistical work professionally, but I remember that it was basically a nightmare to try and collect the right data and use the right variables to get a useful inference. Other engineers on my team would try to improve the models by throwing more variables at them or increasing the number of parameters in the model and I was always pushing back on this. I felt a bit crazy pushing back on this--surely, using more variables and more parameters will make the model fit historical data more closely, and a model which fits historical data more closely will fit future data more closely, and a model which fits future data more closely will be more useful?
Explaining why this is wrong is really hard. I have deep respect for people who are able to explain the principles of statistics and statistical modeling.