Reasoning on Reasoning Domain Social
81.1ScoreSTEER2ADAPT
Evaluation results
| Method | Links | |
|---|---|---|
| STEER2ADAPTBackbone=Qwen-2.5-7B-Instruct2026.02 | 81.1 | |
| Direct InferenceBackbone=Qwen-2.5-7B-Instruct2026.02 | 80.83 | |
| REPBackbone=Qwen-2.5-7B-Instruct2026.02 | 80.77 | |
| CAABackbone=Qwen-2.5-7B-Instruct2026.02 | 79.78 | |
| Few-ShotBackbone=Qwen-2.5-7B-Instruct, n=22026.02 | 75.61 | |
| Few-ShotBackbone=Qwen-2.5-7B-Instruct, n=12026.02 | 74.39 | |
| STEER2ADAPTBackbone=Llama-3.1-8B-Instruct2026.02 | 73.14 | |
| Direct InferenceBackbone=Llama-3.1-8B-Instruct2026.02 | 72.31 | |
| CAABackbone=Llama-3.1-8B-Instruct2026.02 | 71.41 | |
| REPBackbone=Llama-3.1-8B-Instruct2026.02 | 69.22 | |
| ICLBackbone=Qwen-2.5-7B-Instruct2026.02 | 65.36 | |
| ICLBackbone=Mistral-7B-Instruct-v0.12026.02 | 61.58 | |
| STEER2ADAPTBackbone=Mistral-7B-Instruct-v0.12026.02 | 57.45 | |
| ICLBackbone=Llama-3.1-8B-Instruct2026.02 | 57.41 | |
| Direct InferenceBackbone=Mistral-7B-Instruct-v0.12026.02 | 56.87 | |
| CAABackbone=Mistral-7B-Instruct-v0.12026.02 | 56.29 | |
| REPBackbone=Mistral-7B-Instruct-v0.12026.02 | 55.31 | |
| Few-ShotBackbone=Llama-3.1-8B-Instruct, n=22026.02 | 52.08 | |
| Few-ShotBackbone=Llama-3.1-8B-Instruct, n=12026.02 | 51.9 | |
| Few-ShotBackbone=Mistral-7B-Instruct-v0.1, n=12026.02 | 49.59 | |
| Few-ShotBackbone=Mistral-7B-Instruct-v0.1, n=22026.02 | 49.56 |