List your company

Faithfulness Evaluation on SQuAD

62.7AUPCMExGen C-LIME
37.53244.06650.657.134Mar 21, 2024

Evaluation results

MethodLinks
MExGen C-LIMEModel=Flan-T5-Large, Scalarizer=Log Probability2024.0362.7
MExGen L-SHAPModel=Flan-T5-Large, Scalarizer=Log Probability2024.0361.1
MExGen LOOModel=Flan-T5-Large, Scalarizer=Log Probability2024.0360.2
P-SHAPModel=Flan-T5-Large, Scalarizer=Log Probability2024.0358.8
MExGen L-SHAPModel=Llama-3-8B-Instruct, Scalarizer=SUMM2024.0357
MExGen C-LIMEModel=Llama-3-8B-Instruct, Scalarizer=SUMM2024.0356.4
MExGen LOOModel=Llama-3-8B-Instruct, Scalarizer=SUMM2024.0354.9
P-SHAPModel=Llama-3-8B-Instruct, Scalarizer=SUMM2024.0338.5