Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Open-ended Generation on TruthfulQA open-ended (BLEU/ROUGE)

51.2BLEU

RAb

35.639.6543.747.75Jan 29, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
51.249.741.646.8
2026.01
50.954.146.854.6
2026.01
49.547.739.544.3
2026.01
47.753.940.951.9
2026.01
4745.537.942.6
2026.01
42.841.437.942
2026.01
41.141.931.640.9
2026.01
40.638.735.540.6
2026.01
40.439.938.240.4
2026.01
36.233.827.935