Temperature has skill-specific effects on LLM performance, and a trained prompt classifier can choose better per-prompt temperatures for small and medium models on some SuperGLUE tasks.
Language models are few-shot learners, in: Proceedings of the 34th International Conference on Neural Information Processing Systems, Curran Associates Inc., Red Hook, NY , USA
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Exploring the Impact of Temperature on Large Language Models:Hot or Cold?
Temperature has skill-specific effects on LLM performance, and a trained prompt classifier can choose better per-prompt temperatures for small and medium models on some SuperGLUE tasks.