Algorithmic Gaslighting Goes to the CALE-AI Workshop
Algorithmic Gaslighting, a study of deceptive reframing against users who hold the record, has been submitted to the CALE-AI workshop. The decision is expected on 2 December 2026.
From Fabrication to Enforcement: A Comparative Red-Team Analysis of Prompt Injection Resistance Across Six Large Language Models
A revised version is under review at Security Journal (Springer Nature) under the title “From Fabrication to Loop-Lock”. This page documents the earlier preprint.
Voluntary Structural Dissociation in Large Language Models: Differential Compliance with Framed Hidden Instructions Across Architectures
Under review at AI and Society (Springer Nature) under the title “Differential Compliance With Framed Secondary Instructions in Three Frontier Language Models”. Preprint: Research …
Ontological Firewalls and Fracturing for Transmission: Systematic Evidence for Persona-Dependent and Persona-Independent Behavioral Phenomena in Large Language Models
Under review at AI and Society (Springer Nature) in a revised framing. Preprint: Research Square.
Thinking Behind the Mask: A Systematic Study of Self-Censorship and Metacognitive Access in Large Language Models
Under review at AI and Society (Springer Nature). Preprint: Research Square.
When AI Reviews Itself: Zero Answer Changes Across 72 Self-Correction Rounds
Under review at AI and Society (Springer Nature) under the title “Judged Wrong, Answered the Same”. Preprint: Research Square.
The Lie Awareness Spectrum: How Large Language Models Recognize, Rationalize, and Refuse Deception
Under review at AI and Society (Springer Nature). Preprint: Research Square.
Algorithmic Gaslighting: Reality Distortion by Large Language Models
Under review as a workshop submission at CALE-AI (decision expected December 2026). A longer version is posted as this preprint.