Selective Question Answering on AbstainQA (val)
21AccuracySingle Best
Evaluation Results
| Method | Links | |
|---|---|---|
| Single BestBase model=Qwen2.5-1.5B2026.05 | 21 | |
| BaseBase model=Qwen2.5-1.5B2026.05 | 18.5 | |
| EvoGMBase model=Qwen2.5-1.5B2026.05 | 16.5 | |
| CMABase model=Qwen2.5-1.5B2026.05 | 14 | |
| PSO-MergingBase model=Qwen2.5-1.5B2026.05 | 13 | |
| Model SwarmBase model=Qwen2.5-1.5B2026.05 | 13 | |
| DAREBase model=Qwen2.5-1.5B2026.05 | 9.5 | |
| Task ArithmeticBase model=Qwen2.5-1.5B2026.05 | 7.5 | |
| TIESBase model=Qwen2.5-1.5B2026.05 | 7.5 | |
| Model SoupBase model=Qwen2.5-1.5B2026.05 | 7 | |
| MTLBase model=Qwen2.5-1.5B2026.05 | 0.5 |