Across two preregistered studies and six LLMs, most prompt engineering variations produced no reliable improvement in forecasting accuracy, while Bayesian-style prompts consistently hurt performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Prompt Engineering Large Language Models' Forecasting Capabilities
Across two preregistered studies and six LLMs, most prompt engineering variations produced no reliable improvement in forecasting accuracy, while Bayesian-style prompts consistently hurt performance.