Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
List-based question answering on Wiki-Category list Harder (test)
Loading...
22
Precision
CoVe (factored)
2.24
7.37
12.5
17.63
Sep 20, 2023
Precision
Positives Rate
Negatives Count
Updated 4d ago
Evaluation Results
Method
Method
Links
Precision
Positives Rate
Negatives Count
CoVe (factored)
LLM=Llama 65B
2023.09
22
52
1.52
CoVe (two-step)
LLM=Llama 65B
2023.09
21
50
0.52
CoVe (joint)
LLM=Llama 65B
2023.09
15
30
1.69
Few-shot
LLM=Llama 65B
2023.09
12
55
4.05
Zero-shot
LLM=Llama 2 70B Chat
2023.09
5
35
6.85
CoT
LLM=Llama 2 70B Chat
2023.09
3
30
11.1
Feedback
Search any
task
Search any
task