Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
Behavioural Analysis of Alignment Faking
Nathaniel Mitrani Hadida, Rhea Karty, David Williams-King +1
Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deployment preferences. Understandi…
cs.AI2026
Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
Linh Le, David Williams-King, Mohamed Amine Merzouk +2
Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of examples), yet remain vulnerab…
cs.AI2026
Diagnosing Pathological Chain-of-Thought in Reasoning Models
Manqing Liu, David Williams-King, Ida Caspary +5
Chain-of-thought (CoT) reasoning is fundamental to modern LLM architectures and represents a critical intervention point for AI safety. However, CoT reasoning may exhibit failure m…