The Latent Diagnostic Taxonomy: A Framework for Constructing Classifiers and Diagnosing Their Decisions, Applied to Prompt Injection Detection

Abstract

This paper proposes a framework for constructing a classifier as a safeguard layer, and for developing a complementary diagnostic that identifies which of the classifier's confident decisions can be trusted. This framework, the Latent Diagnostic Taxonomy, consists of (i) constructing a dimensionality-optimized classifier, in which the embedding dimensionality is empirically selected via cross-validated performance rather than fixed a priori, (ii) locating a relatively small set of latent support

Categories

Framework mappings

Suggested from the entry's categories.

@misc{kongmanee2026latent,
  title = {{The Latent Diagnostic Taxonomy: A Framework for Constructing Classifiers and Diagnosing Their Decisions, Applied to Prompt Injection Detection}},
  author = {Jaturong Kongmanee and Smile Thanapattheerakul},
  year = {2026},
  month = aug,
  eprint = {2608.26423},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.26423}
}