ResearchBenchmarksRetrieval on OTT-QAFollow47.3PrecisionARM14.0222.6631.339.94Jan 30, 2025Evaluation ResultsMethodMethodLinksPrecisionRecallF1 ScorePR ScoreARMBackbone=Llama3.1-8B-I...Backbone=Llama3.1-8B-Instruct, #calls=1, Avg #obj.=4.982025.0147.379.85562.5ReActBackbone=GPT4o-mini, #...Backbone=GPT4o-mini, #calls=3.68, Avg #obj.=14.52025.0121.780.630.962.7ReActBackbone=Llama3.1-8B-I...Backbone=Llama3.1-8B-It, #calls=4.52, Avg #obj.=19.52025.0115.37623.155.1