Can LLMs learn from a single example?

Re:Can LLMs learn from a single example? by Yenrabbit on Tuesday September 05, 2023 @09:14PM (#37400166)

It does start getting worse at some point right?

[ Parent | on HN ]

Re:Can LLMs learn from a single example? by jph00 on Tuesday September 05, 2023 @09:19PM (#37400214)

I'm sure eventually it would, but we haven't gotten to that point yet in our training.

[ Parent | on HN ]

Re:Can LLMs learn from a single example? by minihat on Wednesday September 06, 2023 @12:18AM (#37401301)

Cross-entropy loss can start getting worse due to the model becoming less calibrated, even as the classification accuracy continues to improve. I first heard that here: https://arxiv.org/abs/1706.04599

Is this 'overconfidence' the leading explanation as to why LLMs continue to show qualitative improvement even after their test loss levels off?

[ Parent | on HN ]

Re:Can LLMs learn from a single example? by alekseiprokopev on Wednesday September 06, 2023 @06:30AM (#37403320)

Is it possible to somehow modify the sampling from the model to account for that?

[ Parent | on HN ]