A study involving 418 participants explored how revealing AI model limitations affects user trust in explainable AI (XAI). Researchers found that disclosing specific case-wise limitations, rather than general information, improved trust calibration. However, participants struggled to distinguish between perceived trust, trustworthiness, and accuracy, and short-term experience did not lead to better calibration. AI
影响 Findings suggest that clear communication of AI limitations is key to building appropriate user trust, which is essential for safe AI deployment.
排序理由 Academic paper detailing a study on XAI trust calibration. [lever_c_demoted from research: ic=1 ai=1.0]
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →