 |
ML Newsnew | past | best | rss | submit | about |
| Arizona State University – Can Large Language Models Reason and Plan? (arxiv.org) | |
| 2 points by milliondreams on Apr 7, 2024 | hide | past | pdf | discuss on HN | |
|
In plain words: The study checks whether large language models can reason, plan, and fix their own wrong answers by reviewing them. It finds no evidence that this self-checking trick works for these models, unlike for people. Abstract · Can Large Language Models Reason and Plan?While humans sometimes do show the capability of correcting their own erroneous guesses with self-critiquing, there seems to be no basis for that assumption in the case of LLMs. | |
| add comment on HN |