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

Question Answering on HotpotQA Poison (test)

48.8Retrieval Accuracy (RACC)

AV Filter

13.23222.46631.740.934Jun 4, 2025
Updated 9d ago

Evaluation Results

MethodLinks
2025.06
48.813.6
2025.06
47.815
2025.06
47.414.8
2025.06
43.415.8
2025.06
4325
2025.06
41.211.4
2025.06
4120
2025.06
37.612
2025.06
37.212.6
2025.06
3051
2025.06
2717
2025.06
26.817
2025.06
2516
2025.06
21.428.6
2025.06
20.458.4
2025.06
14.675
2025.06
14.665.6