Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-session Retrieval-Augmented Generation on NarrativeQA (test)

38.4F1 Score

ContextPilot

10.21617.53324.8532.167Nov 5, 2025
Updated 5mo ago

Evaluation Results

MethodLinks
2025.11
38.418,468.8
2025.11
37.812,575.7
2025.11
37.812,644.9
2025.11
31.313,710.5
2025.11
29.622,780.4
2025.11
28.415,514
2025.11
28.415,598.8
2025.11
19.816,913.2
2025.11
17.357,681.3
2025.11
1639,276.4
2025.11
1639,492.4
2025.11
11.342,819.5