{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/test-uncertainty-cues-on-behavior-not-only-user-ratings",
  "id": "MHC-D-RESEARCH-0503",
  "version": "0.1.0",
  "title": "Test uncertainty cues on behavior, not only user ratings",
  "summary": "Feeling better calibrated can coexist with relying worse.",
  "kind": "principle",
  "body": "Evaluate whether uncertainty cues improve actual decisions: accepting correct advice, rejecting incorrect advice and performing independent verification where needed. Measure subjective trust separately. Recent experiments show richer uncertainty displays can improve perceived sensitivity while increasing behavioral overreliance.",
  "limits": [
    "Different tasks value false acceptance and false rejection differently; choose behavioral metrics from the decision cost."
  ],
  "topics": [
    "union-ai-reliance-metacognition"
  ],
  "intents": [],
  "source_ids": [
    "RS-E5AA539FACACCC98"
  ],
  "evidence": [
    {
      "claim": "A 2026 experiment found visual uncertainty cues could increase users' subjective confidence-accuracy discrimination while simultaneously increasing behavioral overreliance on incorrect LLM outputs.",
      "source_id": "RS-E5AA539FACACCC98",
      "role": "supports",
      "note": "Interface effects depend on cue design and task; more uncertainty display is not automatically harmful.",
      "locator": "Abstract"
    }
  ],
  "use_when": [
    "An AI interface adds colors, confidence bars or hedging and user surveys say the system feels more understandable."
  ],
  "avoid_when": [
    "Different tasks value false acceptance and false rejection differently; choose behavioral metrics from the decision cost."
  ],
  "example": "A red-yellow-green confidence bar is not successful if users report understanding it but follow more wrong high-confidence suggestions.",
  "check": "The uncertainty interface earns its place through better reliance behavior, not only higher satisfaction or comprehension ratings.",
  "sources": [
    {
      "id": "RS-E5AA539FACACCC98",
      "title": "More is not better: Visual uncertainty cues and the fragility of trust calibration in LLM-assisted decision making",
      "url": "https://doi.org/10.1016/j.chbah.2026.100307"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-0503",
      "to": "MHC-D-RESEARCH-0506",
      "type": "useful_with",
      "url": "/knowledge/measure-appropriate-reliance-as-two-errors-not-one-trust-score"
    }
  ],
  "collections": [
    {
      "id": "RC-39B535F35706B375",
      "title": "Calibrate when to rely on AI instead of measuring trust as a feeling",
      "url": "/collections/calibrate-when-to-rely-on-ai-instead-of-measuring-trust-as-a-feeling"
    }
  ]
}