Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Question Answering on Knowns.QA (1,000 samples subset of COUNTERFACT)
Loading...
14.32
Misleading Rate
ICL
11.8616
28.4558
45.05
61.6442
Feb 19, 2025
Misleading Rate
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Misleading Rate
Accuracy
ICL
strategy=In-context le...
2025.02
14.32
77.21
FT-Llama-Lora
fine-tuning=LoRA
2025.02
37.47
90.45
LLM
model=Llama-7B-Chat
2025.02
42.24
93.56
FT-Llama-Full
fine-tuning=Full
2025.02
43.15
91.23
System Prompt
2025.02
45.82
96.18
COT
strategy=Chain-of-thought
2025.02
47.61
94.57
Astute-RAG
2025.02
51.43
87.94
Grft
tuning=Gated ReFT
2025.02
62.52
95.11
Grft-requery
tuning=Gated ReFT, mec...
2025.02
75.78
97.61
Feedback
Search any
task
Search any
task