On the mismatch-grade dataset, all models without the voting mechanism diverge, while AGE with VM estimates student answers increasingly precisely¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? On the MMG dataset, all models without VM went divergent, and the proposed model with VM estimates student answers more and more precisely. → Mohammad Iqbal 2024

Evidence¶

Mohammad Iqbal 2024¶

Mohammad Iqbal, Tsamara Rana Nugraha and Hsing-Kuo Pao. (2024). Active Grade Estimator on Short Answer Assessment. https://doi.org/10.21203/rs.3.rs-5651820/v1

q2 · i? · design · r2

Numerical comparison on the mismatch-grade (MMG) subset of the UNT dataset shown in Fig. 6(b). Models without the voting mechanism diverge; the article reports the proposed model "estimates the student answers more and more precisely".

"As expected, all models w.o. VM went too badly as they were divergent. Even for SS, SC, and SCS prompts, none of them can reduce their errors. With no doubt, the proposed model estimates the student answers more and more precisely; in this case , different grading viewpoints from the multiple teachers."

Discussion¶

Related Claims¶

• The two-stage query with SCS elevates grading process up to 40% on the LL dataset and up to 30% at the beginning on the JRL dataset compared to conventional AL — related
• Instead of cutting answers, the proposed model converges faster than conventional AL and elevates grading up to 30% at the very beginning on the JRL dataset — related
• GPT-4 surpasses other LLMs in the AGE query selection with an accuracy rate 15% better