ResearchBenchmarksTemporal Reasoning on TimeQuestions (test)Follow56.8EMEXAQT10.83222.76634.746.634May 23, 2023Evaluation ResultsMethodMethodLinksEMF1EXAQTEvaluation Protocol=Fi...Evaluation Protocol=Fine-tune2023.0556.8—QAaPBackbone=gpt-3.5-turbo...Backbone=gpt-3.5-turbo, Evaluation Protocol=Few-shot2023.0536.846.7CoTBackbone=gpt-3.5-turbo...Backbone=gpt-3.5-turbo, Evaluation Protocol=Few-shot2023.0528.241.2ReActBackbone=gpt-3.5-turbo...Backbone=gpt-3.5-turbo, Evaluation Protocol=Few-shot2023.0512.617.5