Dual-Lens attention aligns with expert pedagogical focus, allocating most weight to Bloom's taxonomy verbs and problem-solving steps¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person · recheck by 2028: tool and model accuracy changes quickly

Subclaims¶

q2 i? Attention weight analysis shows strong alignment with pedagogical elements, allocating 73% of weights to Bloom's taxonomy verbs and problem-solving steps in mathematics cases, though one failure case placed 28% weight on emotional cues. → Li 2025

Evidence¶

Li 2025¶

Li, Y.; Yang, H.; Fang, Q. (2025). Towards Trustworthy and Explainable-by-Design Large Language Models for Automated Teacher Assessment. Information 2025, 16, 882. https://doi.org/10.3390/info16100882

q2 · i? · design · r2

Interpretability analysis (§5.7, Table 12) of attention weight distributions by pedagogical component; Bloom's verbs receive "73% of weights" against an expert benchmark of 75.4%, while emotional cues receive 28.4% versus an expert benchmark of 15.2%.

"Attention weight analysis reveals strong alignment with pedagogical elements, allocating 73% of weights to Bloom's taxonomy verbs and problem-solving steps in mathematics instruction cases."

Discussion¶

Related Claims¶

• The selected-questions-verbs prompting strategy yields the strongest LLM Bloom classification, reaching weighted F1 up to 0.84 — related
• In-context examples improve LLM Bloom classification: three-shot and ten-shot prompting outperform zero-shot across datasets — related
• Retrained BERT relies on high-impact nouns, verbs, and adjectives for correct predictions, but this reliance is muted on the AF dataset — related
• LLMs show robust zero- and few-shot Bloom classification of OOD AI-assisted questions compared with ML and BERT models — related