Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Faithfulness Evaluation on XSUM
Loading...
22.4
AUPC
MExGen C-LIME
8.88
12.39
15.9
19.41
Mar 21, 2024
AUPC
Updated 4d ago
Evaluation Results
Method
Method
Links
AUPC
MExGen C-LIME
Model=Llama-3-8B-Instr...
2024.03
22.4
MExGen L-SHAP
Model=Llama-3-8B-Instr...
2024.03
22.2
MExGen LOO
Model=Llama-3-8B-Instr...
2024.03
22.1
P-SHAP
Model=Llama-3-8B-Instr...
2024.03
20.2
MExGen L-SHAP
Model=Flan-UL2, Scalar...
2024.03
17.4
MExGen C-LIME
Model=Flan-UL2, Scalar...
2024.03
17.2
MExGen LOO
Model=Flan-UL2, Scalar...
2024.03
16.7
MExGen L-SHAP
Model=DistilBART, Scal...
2024.03
13.8
P-SHAP
Model=Flan-UL2, Scalar...
2024.03
13.7
MExGen C-LIME
Model=DistilBART, Scal...
2024.03
13.6
MExGen LOO
Model=DistilBART, Scal...
2024.03
13.1
P-SHAP
Model=DistilBART, Scal...
2024.03
9.4
Feedback
Search any
task
Search any
task