4 papers
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…
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…
Shape Analysis of Functional Data with Elastic Partial Matching
Darshan Bryner, Anuj Srivastava
Elastic Riemannian metrics have been used successfully in the past for statistical treatments of functional and curve shape data. However, this usage has suffered from an important…
Annotating Motion Primitives for Simplifying Action Search in Reinforcement Learning
Isaac J. Sledge, Darshan W. Bryner, Jose C. Principe
Reinforcement learning in large-scale environments is challenging due to the many possible actions that can be taken in specific situations. We have previously developed a means of…