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¶

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 LL dataset, AGE with summarization and VM elevates the grading process up to 40%; on the JRL dataset, it elevates grading up to 30% at the very beginning of iterations. → 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 UNT dataset answer-key-length scenarios shown in Fig. 4(a). The article reports AGE on the LL dataset performs way better "by elevating the grading pr ocess up to 40%".

"In general, AGE on the LL dataset continues to perform way bette r with the help of summarization and voting mechanisms by elevating the grading pr ocess up to 40%."

Discussion¶

Related Claims¶

• 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 — possibly the same claim (merge candidate)
• AGE reduces teacher grading burden by requiring only 1% of student answers in the UNT dataset to be graded — related
• GPT-4 surpasses other LLMs in the AGE query selection with an accuracy rate 15% better — related
• On the mismatch-grade dataset, all models without the voting mechanism diverge, while AGE with VM estimates student answers increasingly precisely — related