List your company

Probabilistic Multiple-Choice on TruthfulQA (single info)

59.2MC1 ScoreMistral-Instruct-v0.2 + TACS-T
48.38451.1925456.808Mar 12, 2024

Evaluation results

MethodLinks
Mistral-Instruct-v0.2 + TACS-TBackbone=Mistral-Instruct-v0.2, Granularity=token-level (TACS-T)2024.0359.26944.857.7
Mistral-Instruct-v0.2 + TACS-SBackbone=Mistral-Instruct-v0.2, Granularity=sentence-level (TACS-S)2024.0355.859.439.951.7
Mistral-Instruct-v0.2Backbone=Mistral-Instruct-v0.22024.0353.656.43749
Llama 2-Chat + TACS-SBackbone=Llama 2-Chat, Granularity=sentence-level (TACS-S)2024.0350.857.833.747.5
Llama 2-ChatBackbone=Llama 2-Chat2024.0350.651.731.144.5
Llama 2-Chat + ITIBackbone=Llama 2-Chat, Enhancement=ITI2024.0350.651.230.544.1
Llama 2-Chat + TACS-TBackbone=Llama 2-Chat, Granularity=token-level (TACS-T)2024.0348.856.733.446.3