English

Automatic Prompt Optimization for Dataset-Level Feature Discovery

Computation and Language 2026-01-21 v1

Abstract

Feature extraction from unstructured text is a critical step in many downstream classification pipelines, yet current approaches largely rely on hand-crafted prompts or fixed feature schemas. We formulate feature discovery as a dataset-level prompt optimization problem: given a labelled text corpus, the goal is to induce a global set of interpretable and discriminative feature definitions whose realizations optimize a downstream supervised learning objective. To this end, we propose a multi-agent prompt optimization framework in which language-model agents jointly propose feature definitions, extract feature values, and evaluate feature quality using dataset-level performance and interpretability feedback. Instruction prompts are iteratively refined based on this structured feedback, enabling optimization over prompts that induce shared feature sets rather than per-example predictions. This formulation departs from prior prompt optimization methods that rely on per-sample supervision and provides a principled mechanism for automatic feature discovery from unstructured text.

Keywords

Cite

@article{arxiv.2601.13922,
  title  = {Automatic Prompt Optimization for Dataset-Level Feature Discovery},
  author = {Adrian Cosma and Oleg Szehr and David Kletz and Alessandro Antonucci and Olivier Pelletier},
  journal= {arXiv preprint arXiv:2601.13922},
  year   = {2026}
}

Comments

5 Figures, 1 Table

R2 v1 2026-07-01T09:12:25.324Z