Instruction Induction on BigBench Instruction Induction (BBII) (test)
60.14BBII Text Classification ScoreGFLOWPO
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| GFLOWPOPrompt-LM=Mistral-7B, Target-LM=Gemma-7B, Algorithm=GFLOWPO2026.02 | 60.14 | 62.33 | — | |
| StablePromptPrompt-LM=Mistral-7B, Target-LM=Gemma-7B, Algorithm=StablePrompt2026.02 | 57.75 | 57.8 | — | |
| ProTEGIPrompt-LM=Mistral-7B, Target-LM=Gemma-7B, Algorithm=ProTEGI2026.02 | 56.58 | 55.61 | — | |
| APEPrompt-LM=Mistral-7B, Target-LM=Gemma-7B, Algorithm=APE2026.02 | 56.46 | 49.59 | — | |
| ManualPrompt-LM=Mistral-7B, Target-LM=Gemma-7B, Mode=Manual prompting2026.02 | 51.57 | 37.61 | — | |
| Few-shotPrompt-LM=Mistral-7B, Target-LM=Gemma-7B, Mode=Few-shot2026.02 | 51.49 | 6.21 | — |