{
  "id": "2206.02790",
  "version": "v1",
  "published": "2022-06-06T04:04:28.000Z",
  "updated": "2022-06-06T04:04:28.000Z",
  "title": "Improving Model Understanding and Trust with Counterfactual Explanations of Model Confidence",
  "authors": [
    "Thao Le",
    "Tim Miller",
    "Ronal Singh",
    "Liz Sonenberg"
  ],
  "comment": "8 pages, Accepted to IJCAI Workshop on Explainable Artificial Intelligence 2022",
  "categories": [
    "cs.LG",
    "cs.AI",
    "cs.HC"
  ],
  "abstract": "In this paper, we show that counterfactual explanations of confidence scores help users better understand and better trust an AI model's prediction in human-subject studies. Showing confidence scores in human-agent interaction systems can help build trust between humans and AI systems. However, most existing research only used the confidence score as a form of communication, and we still lack ways to explain why the algorithm is confident. This paper also presents two methods for understanding model confidence using counterfactual explanation: (1) based on counterfactual examples; and (2) based on visualisation of the counterfactual space.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-06-06T04:04:28.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "counterfactual explanation",
      "model confidence",
      "improving model understanding",
      "scores help users better understand",
      "confidence scores help users better"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}