Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Claim Verification on HOVER 4-hop
Loading...
73.62
Accuracy
InfoRE + CoT
46.788
53.754
60.72
67.686
Apr 22, 2024
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
InfoRE + CoT
Backbone=GPT-4, Zero-s...
2024.04
73.62
InfoRE
Backbone=GPT-4, Zero-s...
2024.04
73.08
CoT
Backbone=GPT-4, Zero-s...
2024.04
70.68
Standard
Backbone=GPT-4, Zero-s...
2024.04
70.06
InfoRE + CoT
Backbone=GPT-3.5, Zero...
2024.04
65.66
InfoRE
Backbone=GPT-3.5, Zero...
2024.04
64.91
CoT
Backbone=GPT-3.5, Zero...
2024.04
62.69
Standard
Backbone=GPT-3.5, Zero...
2024.04
61.54
InfoRE + CoT
Backbone=LLAMA2-70B, Z...
2024.04
50.15
InfoRE
Backbone=LLAMA2-70B, Z...
2024.04
50.04
CoT
Backbone=LLAMA2-70B, Z...
2024.04
48.01
Standard
Backbone=LLAMA2-70B, Z...
2024.04
47.82
Feedback
Search any
task
Search any
task