Evidence Retrieval on FAKEWIKI RolePlay
63.8Recall@10SCORINGMODEL
Evaluation Results
| Method | Links | |
|---|---|---|
| SCORINGMODELTarget Model=Qwen3-8B2026.05 | 63.8 | |
| SCORINGMODELTarget Model=Llama-3.1-8B2026.05 | 63.4 | |
| STEERFUSETarget Model=Qwen3-8B2026.05 | 60.5 | |
| STEERFUSETarget Model=Llama-3.1-8B2026.05 | 43.5 | |
| BGE-baseTarget Model=Qwen3-8B, Query Type=QA2026.05 | 40.3 | |
| BGE-baseTarget Model=Llama-3.1-8B, Query Type=QA2026.05 | 30.6 | |
| SBERT-MiniLMTarget Model=Qwen3-8B, Query Type=QA2026.05 | 29.1 | |
| SBERT-MPNetTarget Model=Qwen3-8B, Query Type=QA2026.05 | 27.5 | |
| ContrieverTarget Model=Qwen3-8B, Query Type=answer2026.05 | 26.2 | |
| BGE-baseTarget Model=Qwen3-8B, Query Type=answer2026.05 | 26 | |
| Finetuned EmbedSimTarget Model=Llama-3.1-8B2026.05 | 23.6 | |
| SBERT-MiniLMTarget Model=Qwen3-8B, Query Type=answer2026.05 | 23.5 | |
| ContrieverTarget Model=Qwen3-8B, Query Type=QA2026.05 | 22.3 | |
| SBERT-MPNetTarget Model=Llama-3.1-8B, Query Type=QA2026.05 | 21.6 | |
| SBERT-MPNetTarget Model=Qwen3-8B, Query Type=answer2026.05 | 20.3 | |
| SBERT-MiniLMTarget Model=Llama-3.1-8B, Query Type=QA2026.05 | 19.9 | |
| Finetuned EmbedSimTarget Model=Qwen3-8B2026.05 | 16.1 | |
| BGE-baseTarget Model=Llama-3.1-8B, Query Type=answer2026.05 | 11.7 | |
| ContrieverTarget Model=Llama-3.1-8B, Query Type=answer2026.05 | 11.3 | |
| SBERT-MiniLMTarget Model=Llama-3.1-8B, Query Type=answer2026.05 | 10.6 | |
| SBERT-MPNetTarget Model=Llama-3.1-8B, Query Type=answer2026.05 | 9.7 | |
| ContrieverTarget Model=Llama-3.1-8B, Query Type=QA2026.05 | 9.3 | |
| MinHashTarget Model=Qwen3-8B, Query Type=answer2026.05 | 0.1 | |
| MinHashTarget Model=Qwen3-8B, Query Type=QA2026.05 | 0.1 | |
| MinHashTarget Model=Llama-3.1-8B, Query Type=answer2026.05 | 0.1 | |
| MinHashTarget Model=Llama-3.1-8B, Query Type=QA2026.05 | 0.1 |