Faithfulness Evaluation on XSUM
22.4AUPCMExGen C-LIME
Evaluation Results
| Method | Links | |
|---|---|---|
| MExGen C-LIMEModel=Llama-3-8B-Instruct, Scalarizer=SUMM2024.03 | 22.4 | |
| MExGen L-SHAPModel=Llama-3-8B-Instruct, Scalarizer=SUMM2024.03 | 22.2 | |
| MExGen LOOModel=Llama-3-8B-Instruct, Scalarizer=SUMM2024.03 | 22.1 | |
| P-SHAPModel=Llama-3-8B-Instruct, Scalarizer=SUMM2024.03 | 20.2 | |
| MExGen L-SHAPModel=Flan-UL2, Scalarizer=SUMM2024.03 | 17.4 | |
| MExGen C-LIMEModel=Flan-UL2, Scalarizer=SUMM2024.03 | 17.2 | |
| MExGen LOOModel=Flan-UL2, Scalarizer=SUMM2024.03 | 16.7 | |
| MExGen L-SHAPModel=DistilBART, Scalarizer=Log Probability2024.03 | 13.8 | |
| P-SHAPModel=Flan-UL2, Scalarizer=SUMM2024.03 | 13.7 | |
| MExGen C-LIMEModel=DistilBART, Scalarizer=Log Probability2024.03 | 13.6 | |
| MExGen LOOModel=DistilBART, Scalarizer=Log Probability2024.03 | 13.1 | |
| P-SHAPModel=DistilBART, Scalarizer=Log Probability2024.03 | 9.4 |