AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

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 vectors (~ 29% of total training examples) representing influential prompts for identifying tokens

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T09:11:58.312Z. This is not the publication date.