Multi-Hop Question Answering on En.QA
1.41Helmet Correctness ScoreDirect Input
Evaluation Results
| Method | Links | |
|---|---|---|
| Direct InputBase Model=gpt-4o-mini-2024-07-18, Input length (#tokens)=128k2025.05 | 1.41 | |
| ExtAgents (Ours)Base Model=gpt-4o-mini-2024-07-18, Input length (#tokens)=1024k2025.05 | 1.2 | |
| LLM×MapReduceBase Model=gpt-4o-mini-2024-07-18, Input length (#tokens)=256k2025.05 | 1.12 | |
| ExtAgents (Ours)Base Model=Llama-3.1-8B-Instruct, Input length (#tokens)=1024k2025.05 | 1.09 | |
| Direct InputBase Model=Llama-3.1-8B-Instruct, Input length (#tokens)=128k2025.05 | 0.93 | |
| LLM×MapReduceBase Model=Llama-3.1-8B-Instruct, Input length (#tokens)=256k2025.05 | 0.78 | |
| Direct InputBase Model=DeepSeek-R1-Distill-Llama-8B, Input length (#tokens)=32k2025.05 | 0.69 | |
| Chain of AgentsBase Model=Llama-3.1-8B-Instruct, Input length (#tokens)=32k2025.05 | 0.51 |