Score: 1

Submodular Evaluation Subset Selection in Automatic Prompt Optimization

Published: January 7, 2026 | arXiv ID: 2601.03493v1

By: Jinming Nian , Zhiyuan Peng , Hongwei Shang and more

Potential Business Impact:

Finds better ways to ask computers questions.

Business Areas:
Semantic Search Internet Services

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.

Country of Origin
🇺🇸 United States

Repos / Data Links

Page Count
9 pages

Category
Computer Science:
Computation and Language