ResearchBenchmarksSemantic Representation Evaluation on UpWork Narrative Situations Tech. Development (test)Follow96Preference RateOperator0.3225.165074.84Nov 10, 2025Evaluation ResultsMethodMethodLinksPreference RateOperatorCompared Baseline=GLENCompared Baseline=GLEN2025.1196OperatorCompared Baseline=BERT...Compared Baseline=BERT-SRL2025.1196OperatorCompared Baseline=FSTCompared Baseline=FST2025.1186FSTCompared Against=OperatorCompared Against=Operator2025.1114GLENCompared Against=OperatorCompared Against=Operator2025.114BERT-SRLCompared Against=OperatorCompared Against=Operator2025.114