Summarization on Medical (OOV_SD)
26.68R-LCSVOCABADAPT
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| VOCABADAPTBackbone=Llama-3.1-8B, Best Ckpts.=3500, Evaluation Protocol=In-context learning, Demonstration=One exemplar2026.05 | 26.68 | 1.09 | 1.09 | 76.55 | |
| VOCABADAPTBestsetting=zero-shot2026.05 | 26.68 | — | — | 76.55 | |
| CPTOnly (No Vocab Adapt)Backbone=Llama-3.1-8B, Best Ckpts.=7500, Evaluation Protocol=In-context learning, Demonstration=One exemplar2026.05 | 26.29 | 1.25 | 1.25 | 76.22 | |
| VOCABADAPTBackbone=Qwen2.5-7B, Best Ckpts.=3500, Evaluation Protocol=In-context learning, Demonstration=One exemplar2026.05 | 26.11 | 1.12 | 1.11 | 76.15 | |
| CPTOnly (No Vocab Adapt)Backbone=Qwen2.5-7B, Best Ckpts.=8000, Evaluation Protocol=In-context learning, Demonstration=One exemplar2026.05 | 25.96 | 1.28 | 1.29 | 75.9 | |
| Llama-3.1-8B-BASEBest Ckpts.=-, Evaluation Protocol=In-context learning, Demonstration=One exemplar2026.05 | 24.39 | 1.25 | 1.27 | 71.35 | |
| GPT-5-minisetting=zero-shot2026.05 | 23.95 | — | — | 75.07 | |
| Qwen2.5-7B-BASEBest Ckpts.=-, Evaluation Protocol=In-context learning, Demonstration=One exemplar2026.05 | 14.15 | 1.28 | 1.29 | 37.44 |