Single-Document QA on LongBench
25.4NarrativeQA
E2-LLM-Llama2-13B-16k
Updated 2mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2024.01 | 25.4 | 35.3 | 46.5 | 49.1 | - | |
2024.01 | 24.1 | 36.2 | 49 | 52.5 | - | |
2024.01 | 23.6 | 43.3 | 52.3 | 61.2 | - | |
2024.01 | 19.8 | 29.1 | 37.2 | 8.5 | - | |
2024.01 | 19.4 | 26.1 | 38.5 | 43 | - | |
2024.01 | 19.2 | 25.8 | 36.9 | 33.3 | - | |
2024.01 | 19.2 | 33.3 | 42.7 | 47.9 | - | |
2024.01 | 18.9 | 29.9 | 46.2 | 28.4 | - | |
2024.01 | 18.7 | 19.2 | 36.8 | 11.9 | - | |
2024.01 | 16.9 | 27.7 | 41.4 | 29.1 | - | |
2024.01 | 16.4 | 34.7 | 39.1 | 43.6 | - | |
2024.01 | 12.3 | 35.6 | 40.4 | 46.6 | - | |
2025.03 | - | - | - | - | 38.89 | |
2025.03 | - | - | - | - | 47.75 | |
2025.03 | - | - | - | - | 41.91 | |
2025.03 | - | - | - | - | 47.73 | |
2025.03 | - | - | - | - | 47.71 |