Single-hop Question Answering on MFQA en
45.83ScoreLlama-3-8B-Instruct with DCS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Llama-3-8B-Instruct with DCSBackbone=Llama-3-8B-Instruct, Context Strategy=DCS2025.06 | 45.83 | 35.5 | |
| DCSBackbone=Llama-3-8B-Instruct2025.06 | 45.83 | — | |
| Llama-3-8B-Instruct with InfilmBackbone=Llama-3-8B-Instruct, Context Strategy=Infilm2025.06 | 44.94 | 27.15 | |
| InfLLMBackbone=Llama-3-8B-Instruct2025.06 | 44.94 | — | |
| MOICEBackbone=Mistral-7B-Instruct2025.06 | 44.39 | — | |
| Llama-3-8B-InstructBackbone=Llama-3-8B-Instruct, Context Strategy=None2025.06 | 44.3 | 27.6 | |
| Llama-3-8B-InstructBackbone=Llama-3-8B-Instruct, Context Management=Baseline2025.06 | 44.3 | — | |
| InfLLMBackbone=Mistral-7B-Instruct2025.06 | 42.66 | — | |
| DCSBackbone=Mistral-7B-Instruct2025.06 | 42.31 | — | |
| MOICEBackbone=Vicuna-7B2025.06 | 42.29 | — | |
| Mistral-7B-InstructBackbone=Mistral-7B-Instruct, Context Management=Baseline2025.06 | 40.81 | — | |
| DCSBackbone=Vicuna-7B2025.06 | 40.13 | — | |
| Llama-3-8B-Instruct with LM-infiniteBackbone=Llama-3-8B-Instruct, Context Strategy=LM-infinite2025.06 | 40.08 | 24.2 | |
| LM-infiniteBackbone=Llama-3-8B-Instruct2025.06 | 40.08 | — | |
| Llama-3-8B-Instruct with StreamingBackbone=Llama-3-8B-Instruct, Context Strategy=Streaming2025.06 | 40.04 | 24.26 | |
| StreamingBackbone=Llama-3-8B-Instruct2025.06 | 40.04 | — | |
| Vicuna-7BBackbone=Vicuna-7B, Context Management=Baseline2025.06 | 38.24 | — | |
| InfLLMBackbone=Vicuna-7B2025.06 | 37.16 | — | |
| LM-infiniteBackbone=Mistral-7B-Instruct2025.06 | 34.23 | — | |
| StreamingBackbone=Mistral-7B-Instruct2025.06 | 33.87 | — | |
| StreamingBackbone=Vicuna-7B2025.06 | 32.67 | — | |
| LM-InfiniteBackbone=Vicuna-7B2025.06 | 32.3 | — |