Argument Reasoning on ArgsNovel
53.59AccuracyQwen3-4B-Instruct-Arguinas-SFT
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-4B-Instruct-Arguinas-SFTModel Backbone=Qwen3-4B-Instruct, Finetuning Strategy=Continued Finetuning, SFT Data Source=Arguinas2026.03 | 53.59 | |
| Qwen3-8B-Arguinas-Target-SFTModel Backbone=Qwen3-8B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=Arguinas2026.03 | 53.39 | |
| Qwen3-8B-Target-SFTModel Backbone=Qwen3-8B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=Target2026.03 | 53.05 | |
| Qwen3-4B-Arguinas-Target-SFTModel Backbone=Qwen3-4B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=Arguinas2026.03 | 52.52 | |
| Qwen3-4B-Target-SFTModel Backbone=Qwen3-4B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=Target2026.03 | 51.99 | |
| Qwen3-4B-ArgumentOnly-Target-SFTModel Backbone=Qwen3-4B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=ArgumentOnly2026.03 | 49.88 | |
| Qwen3-8B-AAAC-Target-SFTModel Backbone=Qwen3-8B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=AAAC2026.03 | 49.85 | |
| Qwen2.5-7B-InstructModel Backbone=Qwen2.5-7B-Instruct, Finetuning Strategy=Continued Finetuning, SFT Data Source=Baseline2026.03 | 49.72 | |
| Qwen3-4B-AAAC-Target-SFTModel Backbone=Qwen3-4B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=AAAC2026.03 | 49.44 | |
| Qwen3-4B-InstructModel Backbone=Qwen3-4B-Instruct, Finetuning Strategy=Continued Finetuning, SFT Data Source=Baseline2026.03 | 49.3 | |
| Qwen3-4B-EntailmentBank-Target-SFTModel Backbone=Qwen3-4B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=EntailmentBank2026.03 | 49.07 | |
| Qwen2.5-7B-Instruct-Arguinas-SFTModel Backbone=Qwen2.5-7B-Instruct, Finetuning Strategy=Continued Finetuning, SFT Data Source=Arguinas2026.03 | 47.52 | |
| Qwen3-8B-ArgumentOnly-Target-SFTModel Backbone=Qwen3-8B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=ArgumentOnly2026.03 | 46.35 | |
| Qwen3-8B-EntailmentBank-Target-SFTModel Backbone=Qwen3-8B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=EntailmentBank2026.03 | 45.98 |