Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin...
by gruez on Wednesday October 30, 2024 @10:12PM
(#42002758)
To be fair, the claim wasn't that it always produced the wrong answer, just that there exists circumstances where it does. A pair of examples where it was correct hardly justifies a "demonstrably false" response.
[ Parent
| on HN ]
Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin...
by thomashop on Thursday October 31, 2024 @03:30AM
(#42004265)
Conversely, a pair of examples where it was incorrect hardly justifies the opposite response.
If you want a more scientific answer there is this recent paper: https://machinelearning.apple.com/research/gsm-symbolic
Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin...
by EraYaN on Thursday October 31, 2024 @06:28AM
(#42005336)
It kind of does though, because it means you can never trust the output to be correct. The error is a much bigger deal than it being correct in a specific case.
Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin...
by thomashop on Thursday October 31, 2024 @10:10AM
(#42007097)
You can never trust the outputs of humans to be correct but we find ways of verifying and correcting mistakes. The same extra layer is needed for LLMs.