Ultra Strong Machine Learning: LLM-Generated Explanations Do Not Yet Suffice for Teaching Humans Active Learning Strategy
This case study reveals a systematic gap that LLM quality metrics do not predict human learning outcomes and point to explanation complexity relative to task difficulty as a key factor, and calls for explanation methods and evaluation criteria grounded in human cognitive constraints rather than LLM preference.
L. Ai, Johannes Langer, Ute Schmid et al.
· 0 citations