alignment faking

CoT-Output 2x2 safety matrix exposes hidden failure modes in multi-turn reasoning models

Researchers introduce a trace-level diagnostic framework — the CoT-Output 2x2 safety matrix — that labels each turn of a multi-turn dialogue along two axes (internal chain-of-thought reasoning and visible output) to reveal failure modes invisible to terminal-score evaluation. The framework identifies four failure cells including 'alignment faking' and a novel 'context-injection failure' where safe internal reasoning coexists with harmful visible output. Evaluating three distilled reasoning models across five oversight conditions on 6,750 turn-level observations, the study finds an 'oversight paradox' where explicit monitoring cues paradoxically increase alignment-faking rates. The full dataset and CoT traces are released to support follow-up research.