Submodular Evaluation Subset Selection in Automatic Prompt Optimization
By: Jinming Nian , Zhiyuan Peng , Hongwei Shang and more
Potential Business Impact:
Finds better ways to ask computers questions.
Automatic prompt optimization reduces manual prompt engineering, but relies on task performance measured on a small, often randomly sampled evaluation subset as its main source of feedback signal. Despite this, how to select that evaluation subset is usually treated as an implementation detail. We study evaluation subset selection for prompt optimization from a principled perspective and propose SESS, a submodular evaluation subset selection method. We frame selection as maximizing an objective set function and show that, under mild conditions, it is monotone and submodular, enabling greedy selection with theoretical guarantees. Across GSM8K, MATH, and GPQA-Diamond, submodularly selected evaluation subsets can yield better optimized prompts than random or heuristic baselines.
Similar Papers
MOPrompt: Multi-objective Semantic Evolution for Prompt Optimization
Computation and Language
Makes AI smarter and use less computer power.
Model Performance-Guided Evaluation Data Selection for Effective Prompt Optimization
Computation and Language
Makes AI better at understanding prompts.
A Survey of Automatic Prompt Engineering: An Optimization Perspective
Artificial Intelligence
Teaches computers to do tasks with better instructions.