Analytic Essay Scoring on ASAP Essay Set 8
0.67Idea QWKMADRAG
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| MADRAGParadigm=Train-free, Model=GPT-52026.06 | 0.67 | 0.61 | 0.55 | 0.32 | 0.35 | 0.42 | |
| MADRAGParadigm=Train-free, Model=GPT-5-mini2026.06 | 0.6 | 0.63 | 0.62 | 0.28 | 0.34 | 0.36 | |
| MADRAGParadigm=Train-free, Model=GPT-4o-mini2026.06 | 0.59 | 0.47 | 0.6 | 0.65 | 0.55 | 0.58 | |
| MADRAGParadigm=Train-free, Model=GPT-4o2026.06 | 0.59 | 0.42 | 0.63 | 0.61 | 0.59 | 0.62 | |
| FeatEng-RFParadigm=Train2026.06 | 0.58 | 0.63 | 0.54 | 0.55 | 0.58 | 0.55 | |
| ProTACTParadigm=Train2026.06 | 0.57 | 0.61 | — | 0.59 | 0.55 | 0.43 | |
| Human-Human2026.06 | 0.53 | 0.54 | 0.47 | 0.48 | 0.51 | 0.55 | |
| MADRAGParadigm=Train-free, Model=GPT-3.5-turbo2026.06 | 0.52 | 0.43 | 0.52 | 0.55 | 0.41 | 0.49 | |
| ZS-LLMParadigm=Train-free, Model=LLaMA-2-13B-Chat2026.06 | 0.27 | 0.27 | 0.27 | 0.26 | 0.12 | 0.08 | |
| ZS-LLMParadigm=Train-free, Model=GPT-3.5-turbo2026.06 | 0.18 | 0.25 | 0.15 | 0.15 | 0.2 | 0.31 |