Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Attributed Question Answering on ELI5 (test)
Loading...
21.3
Rouge-L
Zero-Shot
16.724
17.912
19.1
20.288
Nov 18, 2025
Rouge-L
MAUVE
EM Rec.
Correct in P
Citation F1
Updated 4d ago
Evaluation Results
Method
Method
Links
Rouge-L
MAUVE
EM Rec.
Correct in P
Citation F1
Zero-Shot
Backbone=Mistral-Orca-...
2025.11
21.3
35
22.2
12.6
10.4
Calf
Source Domain=ASQA, Ba...
2025.11
21.2
31.3
20.4
12.5
57.3
FineRef
Source Domain=ASQA, Ba...
2025.11
21
32.4
23.6
13.4
59.1
Few-shot FT
Source Domain=ASQA, Ba...
2025.11
20.9
41.1
19.7
10.6
40.4
Self-RAG 7B
Backbone=Mistral-Orca-...
2025.11
16.9
32.6
9.7
5.4
27.6
Feedback
Search any
task
Search any
task