A comparison of chain-of-thought reasoning strategies across datasets and models
Emergent chain-of-thought (CoT) reasoning capabilities promise to improve the performance and explainability of large language models (LLMs). However, uncertainties remain about how reasoning strategies formulated for previous model generations generalize to new model generations and different datas...
| Prif Awduron: | , , , |
|---|---|
| Fformat: | Erthygl |
| Iaith: | English |
| Cyhoeddwyd: |
PeerJ Inc.
2024-04-01
|
| Cyfres: | PeerJ Computer Science |
| Pynciau: | |
| Mynediad Ar-lein: | https://peerj.com/articles/cs-1999.pdf |