Argument Component Classification on UKP Student Essays (test)
89.5Macro F1Cabessa et al. (2025)
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Cabessa et al. (2025)paradigm=Supervised Reference2026.03 | 89.5 | — | — | — | — | |
| MAD-ACCparadigm=Inference-Only Baselines2026.03 | 85.7 | 87 | 92 | 74.5 | 90.7 | |
| Baseline C (Smart Reasoning)paradigm=Inference-Only Baselines, prompting=Smart Reasoning2026.03 | 84.9 | 86.1 | 92.2 | 72.5 | 90.1 | |
| Baseline B (Chain-of-Thought)paradigm=Inference-Only Baselines, prompting=Chain-of-Thought2026.03 | 79.2 | 81.2 | 91.4 | 58.5 | 87.8 | |
| Baseline A (Vanilla)paradigm=Inference-Only Baselines, prompting=Vanilla2026.03 | 78.5 | 80.8 | 90.6 | 57 | 88 |