Chat on IFEval
48.8Loose Prompt MetricFine-tuned
Evaluation Results
| Method | Links | |
|---|---|---|
| Fine-tunedCR=1, Backbone=LLaMA3-8B, Fine-tuned Model=LLaMA3-Instruct-8B2025.04 | 48.8 | |
| Fine-tunedCR=1, Backbone=LLaMA2-13B, Fine-tuned Model=LLaMA2-Chat-13B2025.04 | 33.64 | |
| IMPARTCR=32, Backbone=LLaMA3-8B, Fine-tuned Model=LLaMA3-Instruct-8B2025.04 | 33.27 | |
| Fine-tunedCR=1, Backbone=LLaMA2-7B, Fine-tuned Model=LLaMA2-Chat-7B2025.04 | 31.79 | |
| DARECR=32, Backbone=LLaMA3-8B, Fine-tuned Model=LLaMA3-Instruct-8B2025.04 | 30.5 | |
| LowRankCR=32, Backbone=LLaMA3-8B, Fine-tuned Model=LLaMA3-Instruct-8B2025.04 | 29.39 | |
| IMPARTCR=32, Backbone=LLaMA2-7B, Fine-tuned Model=LLaMA2-Chat-7B2025.04 | 27.91 | |
| IMPARTCR=32, Backbone=LLaMA2-13B, Fine-tuned Model=LLaMA2-Chat-13B2025.04 | 26.8 | |
| LowRankCR=32, Backbone=LLaMA2-13B, Fine-tuned Model=LLaMA2-Chat-13B2025.04 | 26.06 | |
| DARECR=32, Backbone=LLaMA2-13B, Fine-tuned Model=LLaMA2-Chat-13B2025.04 | 24.77 | |
| LowRankCR=32, Backbone=LLaMA2-7B, Fine-tuned Model=LLaMA2-Chat-7B2025.04 | 23.84 | |
| BackboneCR=1, Backbone=LLaMA2-7B, Fine-tuned Model=LLaMA2-Chat-7B2025.04 | 20.52 | |
| BackboneCR=1, Backbone=LLaMA2-13B, Fine-tuned Model=LLaMA2-Chat-13B2025.04 | 19.04 | |
| DARECR=32, Backbone=LLaMA2-7B, Fine-tuned Model=LLaMA2-Chat-7B2025.04 | 16.82 | |
| BackboneCR=1, Backbone=LLaMA3-8B, Fine-tuned Model=LLaMA3-Instruct-8B2025.04 | 11.46 |