Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
PRP Faithfulness Evaluation on Eve 30 persona statements (original characters)
Loading...
0.7
ΔAPC (DeB)
Gemma-7B
0.496
1.873
3.25
4.627
May 13, 2024
ΔAPC (DeB)
ΔAPC (GPT-4)
Human Score
Updated 4d ago
Evaluation Results
Method
Method
Links
ΔAPC (DeB)
ΔAPC (GPT-4)
Human Score
Gemma-7B
CPO (APC-based DPO)=False
2024.05
0.7
-0.2
2
Experience Upload (EU)
CPO (APC-based DPO)=False
2024.05
3.6
0.7
4.6
Long-context Memory (LCM)
CPO (APC-based DPO)=False
2024.05
3.9
0.7
5
Experience Upload (EU)
CPO (APC-based DPO)=True
2024.05
3.9
0.9
5.2
Retrieval-augmented Generation (RAG)
CPO (APC-based DPO)=False
2024.05
4.8
2.4
5.8
Long-context Memory (LCM)
CPO (APC-based DPO)=True
2024.05
5.1
3.3
6.6
Retrieval-augmented Generation (RAG)
CPO (APC-based DPO)=True
2024.05
5.8
4.2
7
Feedback
Search any
task
Search any
task