Open-book Question Answering on OpenBookQA n=991 (20%)
57.52AccuracyMTO-MP
Evaluation results
| Method | Links | |
|---|---|---|
| MTO-MPEvaluation Protocol=Fine-Tuning, Backbone=T5-large, Adaptation Objective=Denoising2026.06 | 57.52 | |
| MVP-Tuning2026.06 | 56 | |
| T5-large (baseline)Evaluation Protocol=Fine-Tuning, Backbone=T5-large2026.06 | 55.31 | |
| MTO-MCPEvaluation Protocol=Fine-Tuning, Backbone=T5-large, Adaptation Objective=LM2026.06 | 54.3 | |
| MTO-APEvaluation Protocol=Fine-Tuning, Backbone=T5-large, Adaptation Objective=LM2026.06 | 53 | |
| SAFE2026.06 | 44.93 | |
| QA-GNN2026.06 | 42.4 | |
| GSC2026.06 | 42.4 | |
| GreaseLM2026.06 | 42.2 | |
| RoBERTa-largeBackbone=RoBERTa-large2026.06 | 41.47 | |
| MHGRN2026.06 | 39.73 | |
| MTO-PreMAPEvaluation Protocol=Prompt-Tuning, Backbone=T5-large, Adaptation Objective=LM2026.06 | 39.65 | |
| MTO-PreAPEvaluation Protocol=Prompt-Tuning, Backbone=T5-large, Adaptation Objective=LM2026.06 | 32.42 |