Question Answering on XQuAD English Distractor I - (X), Q(X & EN) (Avg)
98.23Language ConsistencyBloom-7.1B (Selective SFT)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Bloom-7.1B (Selective SFT)Model=Bloom-7.1B, Fine-tuning Strategy=Selective SFT2026.01 | 98.23 | 6.95 | |
| Qwen-3-32B (Selective SFT)Model=Qwen-3-32B, Fine-tuning Strategy=Selective SFT2026.01 | 97.62 | 18.05 | |
| Bloom-7.1B (Full scope SFT)Model=Bloom-7.1B, Fine-tuning Strategy=Full scope SFT2026.01 | 97.03 | 6.96 | |
| Qwen-3-32B (Full scope SFT)Model=Qwen-3-32B, Fine-tuning Strategy=Full scope SFT2026.01 | 75.99 | 17.77 | |
| Bloom-7.1B (Pre-Finetuning)Model=Bloom-7.1B, Fine-tuning Strategy=Pre-Finetuning2026.01 | 69.44 | 0.67 | |
| Qwen-3-32B (Pre-Finetuning)Model=Qwen-3-32B, Fine-tuning Strategy=Pre-Finetuning2026.01 | 41.99 | 15.81 | |
| Qwen-3-32B (Random Selective SFT)Model=Qwen-3-32B, Fine-tuning Strategy=Random Selective SFT2026.01 | 37.78 | 0 | |
| Bloom-7.1B (Random Selective SFT)Model=Bloom-7.1B, Fine-tuning Strategy=Random Selective SFT2026.01 | 26.16 | 0 |