Generation-based extraction yields superior emotion vectors in small LMs that localize in middle layers following a U-shaped curve and enable architecture-dependent steering with three distinct behavioral regimes.
Model medicine: A clinical framework for understanding, diagnosing, and treating AI models.arXiv preprint arXiv:2603.04722,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
M-CARE provides a medical-inspired reporting system for AI behavioral disorders, demonstrated through 20 cases and a validated experiment showing shell instructions overriding cooperative behavior across game domains.
citing papers explorer
-
Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison
Generation-based extraction yields superior emotion vectors in small LMs that localize in middle layers following a U-shaped curve and enable architecture-dependent steering with three distinct behavioral regimes.
-
M-CARE: Standardized Clinical Case Reporting for AI Model Behavioral Disorders, with a 20-Case Atlas and Experimental Validation
M-CARE provides a medical-inspired reporting system for AI behavioral disorders, demonstrated through 20 cases and a validated experiment showing shell instructions overriding cooperative behavior across game domains.