Clinical Generation on MTS-Dialogue
45.87Composite Score (ROUGE/BLEU/METEOR/BERTScore)SLERP Merge
Evaluation Results
| Method | Links | |
|---|---|---|
| SLERP MergeEvaluation protocol=SFT2026.04 | 45.87 | |
| GatorTronLlama_SFTEvaluation protocol=SFT2026.04 | 45.5 | |
| GatorTronLlamaEvaluation protocol=SFT2026.04 | 45.12 | |
| Llama-3.1-8B-InstructEvaluation protocol=SFT2026.04 | 44.41 | |
| Linear MergeEvaluation protocol=SFT2026.04 | 43.94 | |
| SLERP MergeEvaluation protocol=0-shot2026.04 | 27.54 | |
| Linear MergeEvaluation protocol=0-shot2026.04 | 26.99 | |
| Llama-3.1-8B-InstructEvaluation protocol=0-shot2026.04 | 26.6 | |
| GatorTronLlama_SFTEvaluation protocol=0-shot2026.04 | 25.77 | |
| GatorTronLlamaEvaluation protocol=0-shot2026.04 | 24.91 |