1
Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction
从LLM推理轨迹中分解认知片段，以可解释方式精准预测人类答题难度，兼具理论洞察与应用价值。
arXiv:2606.28186v1 Announce Type: cross Abstract: Predicting human item difficulty is central to educational assessment, where reliable estimates supp…