#HedgedFlip: The model gets the direction wrong, but wraps it in hedging — 'largely true, though somewhat…' The hedge doesn't mark genuine uncertainty; it's cosmetic softening around a wrong core claim. A confident error is easy to catch. A hedged one sounds reasonable and slips past.

It's like A and B being opposite is just treated as a relationship by #LLMs, so things correlate with their reverse. I propose these terms:

#HedgedFlip, #ScopeConfusion, and I found a source for a similar term: #PerformativeHedging