ResearchBenchmarksLearning Outcome Assessment on User Study N=24 (within-subject)For AI assistantsMarkdownContent indexLearning Outcome Assessment on User Study N=24 (within-subject)Follow6.17SatisfactionCanAnswer5.655.7855.926.055Dec 10, 2025Evaluation resultsMethodMethodLinksSatisfactionUsefulnessReliabilityCanAnswerScale=7-point Likert s...Scale=7-point Likert scale, Statistical Test=Mann-Whitney U test, Measurement=Mean (SD)2025.126.176.256BaselineScale=7-point Likert s...Scale=7-point Likert scale, Statistical Test=Mann-Whitney U test, Measurement=Mean (SD)2025.125.675.755.17