Appending learning objectives to questions improves Bloom classification on the AF dataset¶

Claim · All claims
Evidence · 1 study · causal r1 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? Concatenating learning objectives with questions substantially improved classification on AF, raising BERT from 0.30 to 0.40 macro F1. → Michael Lawrence Castanares 2026

Evidence¶

Michael Lawrence Castanares 2026¶

Michael Lawrence Castanares, Princess Ventures, and Allan Tan. (2026). Evaluation of Pre-trained Models for Pedagogical Assessment of NovelAI-Assisted Educational Questions. Preprint. https://arxiv.org/abs/2609.27749 doi:10.48550/arxiv.2609.27749

q2 · i? · causal · r1

Feature-engineering experiment (Configuration C, question + learning objective) on the AF dataset, reported in Results Table 5; BERT improved from 0.30 baseline to 0.40 with LO. No effect sizes printed.

"With the AF dataset, we found that adding the learning objective to the questions substantially improved classification performance."

Discussion¶

Related Claims¶

• 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
• Feature-based ML Bloom classifiers trained on IID data degrade sharply on out-of-distribution AI-assisted questions — related
• Model retraining on labeled OOD data provides the largest improvement in Bloom classification across models and datasets — related
• Text splicing into single sentences improves ML and BERT Bloom classification on the Scaria OOD dataset — related