SOURCE-LINKED INTELLIGENCE

Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust Prediction

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Clinical language models can achieve strong in-hospital accuracy yet fail under deployment shifts because they exploit note-specific artifacts (e.g., templates, separators, boilerplate) that do not reflect patient state. We propose CAST (Concept-guided Artifact Suppression Tuning), an SAE-based framework for auditable clinical text classification. CAST uses Sparse Autoencoders to expose sparse, human-auditable features from intermediate Transformer activations, labels SAE latents with an LLM-assisted interpretation pipeline and ICD-10 retrieval constraints, suppresses verified artifact latents

Read original source ↗ Open in workspace

recordType

paper

region

Global