ResearchBenchmarksSummary Similarity Evaluation on GPT generated summaries 5.1Follow86.5BERTScore-F1AutoMUP85.35685.65385.9586.247Apr 8, 2026Evaluation ResultsMethodMethodLinksBERTScore-F1SBERT SimilaritySimCSE SimilarityUSE SimilarityROUGE-LBLEURT ScoreAutoMUPConsensus level=A1Consensus level=A12026.0486.565.596.865.118.238.3AutoMUPConsensus level=A2Consensus level=A22026.0485.858.596.86014.229AutoMUPConsensus level=A3Consensus level=A32026.0485.458.596.757.813.325.9