Multi-hop Question Answering on MuSiQue 23 (test)
0.5p-hatSPECHOP
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| SPECHOPTarget Tool (T)=Web Search, Speculator (S)=GPT-4o2026.05 | 0.5 | 0.19 | 0.11 | 0.63 | 0.69 | |
| SPECHOPTarget Tool (T)=Web Search, Speculator (S)=GPT-4o mini2026.05 | 0.49 | 0.2 | 0.11 | 0.65 | 0.72 | |
| SPECHOPTarget Tool (T)=E5 Retrieval, Speculator (S)=Llama 3.1 8B2026.05 | 0.42 | 0.3 | 0.64 | 0.82 | 0.86 | |
| SPECHOPTarget Tool (T)=Web Search, Speculator (S)=Llama 3.1 8B2026.05 | 0.41 | 0.05 | 0.11 | 0.65 | 0.72 | |
| SPECHOPTarget Tool (T)=E5 Retrieval, Speculator (S)=Qwen 3 8B2026.05 | 0.34 | 0.29 | 0.64 | 0.85 | 0.89 | |
| SPECHOPTarget Tool (T)=Web Search, Speculator (S)=Qwen 3 8B2026.05 | 0.33 | 0.05 | 0.11 | 0.72 | 0.78 |