Cross-Dataset Bloom Question Classification: Supervised Models and Prompted LLMs
📰 ArXiv cs.AI
Learn to classify assessment questions using Bloom's taxonomy with supervised models and prompted LLMs, and understand their generalizability across datasets
Action Steps
- Build a supervised model using machine learning algorithms to classify assessment questions into Bloom's taxonomy categories
- Run experiments to evaluate the model's performance on within-dataset and cross-dataset settings
- Configure a prompted LLM to classify assessment questions and compare its performance with supervised models
- Test the generalizability of both approaches across different datasets and question types
- Apply the best-performing approach to real-world question classification tasks and evaluate its effectiveness
Who Needs to Know This
Educators, instructional designers, and AI researchers can benefit from this knowledge to automate question classification and reduce instructor workload. The team can use this to develop more accurate and generalizable question classification systems.
Key Insight
💡 Supervised models and prompted LLMs can be effective for Bloom question classification, but their generalizability across datasets is crucial for real-world applications
Share This
Classify assessment questions with Bloom's taxonomy using supervised models & prompted LLMs! #AIinEducation #QuestionClassification
Key Takeaways
Learn to classify assessment questions using Bloom's taxonomy with supervised models and prompted LLMs, and understand their generalizability across datasets
Full Article
Title: Cross-Dataset Bloom Question Classification: Supervised Models and Prompted LLMs
Abstract:
arXiv:2606.13684v1 Announce Type: cross Abstract: Automatic Bloom's taxonomy classification of assessment questions can substantially reduce instructor workload, but labeling is subjective and teacher-dependent. Prior machine learning (ML) and deep learning (DL) approaches reported strong within-dataset results, yet were rarely evaluated in cross-dataset settings, leaving real-world generalizability unclear; meanwhile, LLM effectiveness for Bloom question classification has not been systematical
Abstract:
arXiv:2606.13684v1 Announce Type: cross Abstract: Automatic Bloom's taxonomy classification of assessment questions can substantially reduce instructor workload, but labeling is subjective and teacher-dependent. Prior machine learning (ML) and deep learning (DL) approaches reported strong within-dataset results, yet were rarely evaluated in cross-dataset settings, leaving real-world generalizability unclear; meanwhile, LLM effectiveness for Bloom question classification has not been systematical
DeepCamp AI