Text Generation on DomainBench Medicine
0.701BERTScoreTF-TTCL
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| TF-TTCL2026.04 | 0.701 | -0.4315 | 0.0427 | 0.2222 | 0.0739 | 0.1636 | |
| EATA2026.04 | 0.691 | -0.8199 | 0.0168 | 0.1663 | 0.0217 | 0.1226 | |
| Tent2026.04 | 0.6763 | -0.7904 | 0.0206 | 0.1668 | 0.0276 | 0.1139 | |
| COME2026.04 | 0.67 | -0.8686 | 0.0156 | 0.1526 | 0.0192 | 0.1061 | |
| Llama-3.1-8B-Instructstatus=Base Model2026.04 | 0.6642 | -0.7026 | 0.0154 | 0.1507 | 0.0328 | 0.0986 | |
| TF-GRPO2026.04 | 0.6641 | -0.5962 | 0.0126 | 0.1244 | 0.034 | 0.0845 | |
| TLM2026.04 | 0.6638 | -0.7151 | 0.0157 | 0.1532 | 0.0321 | 0.1004 |