
This dataset contains the expert evaluations and learner detectability assessments used to analyze instructional risk in LLM-generated outputs. It includes annotations of instructional failure modes, severity scores, propagation risk ratings, and learner judgments of correctness and reuse intention. These data form the empirical basis for computing the Instructional Risk Index (IRI) and for examining cross-domain risk patterns and learner susceptibility to pedagogically misleading outputs.
Educational AI Safety Assessment, Instructional Risk Index (IRI), LLM Pedagogical Failure Modes, Expert Evaluation Dataset, Instructional Risk Analysis
Educational AI Safety Assessment, Instructional Risk Index (IRI), LLM Pedagogical Failure Modes, Expert Evaluation Dataset, Instructional Risk Analysis
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
