Argument Quality Evaluation on WebisCMV 20
56.7AccuracyQwen3-8B-Arguinas-Target-SFT
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-8B-Arguinas-Target-SFTModel Backbone=Qwen3-8B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=Arguinas2026.03 | 56.7 | |
| Qwen3-4B-Arguinas-Target-SFTModel Backbone=Qwen3-4B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=Arguinas2026.03 | 56.03 | |
| Qwen3-4B-ArgumentOnly-Target-SFTModel Backbone=Qwen3-4B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=ArgumentOnly2026.03 | 55.45 | |
| Qwen3-4B-EntailmentBank-Target-SFTModel Backbone=Qwen3-4B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=EntailmentBank2026.03 | 55.33 | |
| Qwen3-4B-Target-SFTModel Backbone=Qwen3-4B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=Target2026.03 | 53.8 | |
| Qwen3-4B-Instruct-Arguinas-SFTModel Backbone=Qwen3-4B-Instruct, Finetuning Strategy=Continued Finetuning, SFT Data Source=Arguinas2026.03 | 53.42 | |
| Qwen3-4B-AAAC-Target-SFTModel Backbone=Qwen3-4B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=AAAC2026.03 | 53.34 | |
| Qwen3-8B-Target-SFTModel Backbone=Qwen3-8B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=Target2026.03 | 53.3 | |
| Qwen2.5-7B-Instruct-Arguinas-SFTModel Backbone=Qwen2.5-7B-Instruct, Finetuning Strategy=Continued Finetuning, SFT Data Source=Arguinas2026.03 | 52.58 | |
| Qwen3-4B-InstructModel Backbone=Qwen3-4B-Instruct, Finetuning Strategy=Continued Finetuning, SFT Data Source=Baseline2026.03 | 52.5 | |
| Qwen3-8B-AAAC-Target-SFTModel Backbone=Qwen3-8B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=AAAC2026.03 | 51.46 | |
| Qwen2.5-7B-InstructModel Backbone=Qwen2.5-7B-Instruct, Finetuning Strategy=Continued Finetuning, SFT Data Source=Baseline2026.03 | 50.63 | |
| Qwen3-8B-ArgumentOnly-Target-SFTModel Backbone=Qwen3-8B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=ArgumentOnly2026.03 | 50.57 | |
| Qwen3-8B-EntailmentBank-Target-SFTModel Backbone=Qwen3-8B, Finetuning Strategy=Pre-adaptive Finetuning, SFT Data Source=EntailmentBank2026.03 | 50.22 |