Tracing on WMDP (test)
100TSRROUGE-L
Evaluation Results
| Method | Links | |
|---|---|---|
| ROUGE-LBase Model=Llama-3-8B2026.03 | 100 | |
| SBERTBase Model=Llama-3-8B2026.03 | 100 | |
| Llama-3.2-1BBase Model=Llama-3-8B2026.03 | 100 | |
| DEBUGLMBase Model=Llama-3-8B2026.03 | 100 | |
| ROUGE-LBase Model=Qwen-3-8B2026.03 | 100 | |
| SBERTBase Model=Qwen-3-8B2026.03 | 100 | |
| Llama-3.2-1BBase Model=Qwen-3-8B2026.03 | 100 | |
| DEBUGLMBase Model=Qwen-3-8B2026.03 | 100 | |
| BM25Base Model=Llama-3-8B2026.03 | 0 | |
| BM25Base Model=Qwen-3-8B2026.03 | 0 |