Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Closed-Book Question Answering on HotpotQA
Loading...
39.6
Recall
AGDLRPh
31.592
33.671
35.75
37.829
Sep 30, 2025
Recall
EM
F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Recall
EM
F1
AGDLRPh
Backbone=Llama 3.1 (8B)
2025.09
39.6
-
-
Greedy
Backbone=Llama 3.1 (8B)
2025.09
34.6
-
-
DoLA
Backbone=Llama 3.1 (8B)
2025.09
34.3
-
-
Nucleus
Backbone=Llama 3.1 (8B)
2025.09
31.9
-
-
Standard-prompting (no-rationale)
Prompting strategy=no-...
2022.03
-
27.1
36.8
CoT-prompting
Prompting strategy=Cha...
2022.03
-
28.9
39.8
Self-consistency
Prompting strategy=Sel...
2022.03
-
33.8
44.6
Feedback
Search any
task
Search any
task