Summarization on Legal (OOV_RS)
24.86R-LCSLlama-3.1-8B-BASE
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Llama-3.1-8B-BASEBest Ckpts.=-, Evaluation Protocol=In-context learning, Demonstration=One exemplar2026.05 | 24.86 | 1.06 | 1.08 | 65.28 | |
| CPTOnly (No Vocab Adapt)Backbone=Qwen2.5-7B, Best Ckpts.=10500, Evaluation Protocol=In-context learning, Demonstration=One exemplar2026.05 | 24.72 | 1.09 | 1.12 | 67.97 | |
| CPTOnly (No Vocab Adapt)Backbone=Llama-3.1-8B, Best Ckpts.=10000, Evaluation Protocol=In-context learning, Demonstration=One exemplar2026.05 | 24.36 | 1.06 | 1.08 | 68.38 | |
| VOCABADAPTBackbone=Llama-3.1-8B, Best Ckpts.=6500, Evaluation Protocol=In-context learning, Demonstration=One exemplar2026.05 | 23.92 | 1.01 | 1.01 | 68.11 | |
| VOCABADAPTBestsetting=zero-shot2026.05 | 23.92 | — | — | 68.11 | |
| VOCABADAPTBackbone=Qwen2.5-7B, Best Ckpts.=6500, Evaluation Protocol=In-context learning, Demonstration=One exemplar2026.05 | 23.22 | 1.04 | 1.05 | 66.89 | |
| GPT-5-minisetting=zero-shot2026.05 | 20.46 | — | — | 67.08 | |
| Qwen2.5-7B-BASEBest Ckpts.=-, Evaluation Protocol=In-context learning, Demonstration=One exemplar2026.05 | 9.9 | 1.09 | 1.12 | 27.15 |