A context-rich prompt matched or beat most reasoning prompts on the tested short and long forecasting tasks, and no prompting style won everywhere.
Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Context information can be more important than reasoning for time series forecasting with a large language model
A context-rich prompt matched or beat most reasoning prompts on the tested short and long forecasting tasks, and no prompting style won everywhere.