A generation-then-judge LLM pipeline can produce taxonomy-targeted synthetic wrong answers for quantitative questions, though targeted errors are harder than free-form ones and real-student validity is untested.
arXiv preprint arXiv:2501.10365 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Compares LLMs against semantic similarity for binary classification of student self-explanations in programming education.
citing papers explorer
-
Taxonomy-Targeted Error Generation for Quantitative Reasoning
A generation-then-judge LLM pipeline can produce taxonomy-targeted synthetic wrong answers for quantitative questions, though targeted errors are harder than free-form ones and real-student validity is untested.
-
Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self Explanations in Programming Education
Compares LLMs against semantic similarity for binary classification of student self-explanations in programming education.