News for hackers. Stuff that matters.

A comment on Show HN: Open-source model and scorecard for measuring hallucinations in LLMs. Parent comment

Re:Show HN: Open-source model and scorecard for measuring ha... by forrestbao on Monday November 06, 2023 @04:33PM (#38169336)
A smaller model has less capacity and thus is less prone to overfitting, which is a reason of hallucination. Overfitting means that a model cannot adjust its output based on the input that is unseen during training.
[ Parent | on HN ]
Re:Show HN: Open-source model and scorecard for measuring ha... by simonhughes22 on Monday November 06, 2023 @04:38PM (#38169388)
Yes. Just because the model is smaller doesn't always mean by default it's worse, as they may be trained for less time or on less data, which in some cases could be beneficial. The differences are small so may not be statistically significant. Plus the model is doing the evaluation, so while it's highly correlated with humans, a small difference like this may not mean that the the 7B model is necessarily better.
[ Parent | on HN ]