Support Indicator

A visual or textual cue that communicates the degree of agreement across multiple AI model responses for a particular claim. Support indicators help BLV users assess claim reliability by showing how many or which models agree. Research has explored four types: source-based ("3 of 3 GPT, 2 of 3 Gemini"), percentage-based ("56% of responses"), language-based ("well-supported" or "poorly supported"), and no indicator. Source-based indicators were slightly preferred overall because they provide transparency about which specific models agree, though preferences varied significantly among individual users. Support indicators transform raw variation data into actionable reliability signals.