A Bayesian 'knowledge gradient' policy for sequentially choosing which prompts to evaluate finds better language-model prompts within 30 evaluations than evolutionary, bandit, and greedy baselines on instruction-induction tasks.
Language models are few-shot learners
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
-
A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models
A Bayesian 'knowledge gradient' policy for sequentially choosing which prompts to evaluate finds better language-model prompts within 30 evaluations than evolutionary, bandit, and greedy baselines on instruction-induction tasks.