Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models
Frank E. Bobe, Gregory D. Vetaw, Darshan W. Bryner +2
Activation steering modifies LLM behavior at inference time, but identifying where and how strongly to steer remains manual. We introduce Deep Noir, a framework that uses Logit Len…
cs.AI2026
Diagnosing Generalization Failures in Fine-Tuned LLMs: A Cross-Architectural Study on Phishing Detection
Frank Bobe, Gregory D. Vetaw, Chase Pavlick +3
The practice of fine-tuning Large Language Models (LLMs) has achieved state-of-the-art performance on specialized tasks, yet diagnosing why these models become brittle and fail to…