Self-Consistency

A prompting technique for large language models in which the model is queried multiple times with the same input (using non-deterministic sampling) and the most frequent or highest-voted answer is returned as the final output. Self-consistency reduces hallucination and variance, which is particularly valuable in accessibility-testing contexts where a misclassified component could leave a real barrier undetected or flood developers with false positives. VisualDroid, for example, uses 10 rounds per reasoning hop to stabilise its output.