Logical Reasoning on FOLIO-SEMEVAL Subtask 1 (evaluation)
93.19AccuracyNL
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| NLNotation=NL, Backbone=Flan-T5-large2026.06 | 93.19 | 9.57 | 27.74 | |
| NL-FOLNotation=NL-FOL, Backbone=Flan-T5-large2026.06 | 90.57 | 8.55 | 27.8 | |
| NL-CLIFNotation=NL-CLIF, Backbone=Flan-T5-large2026.06 | 89 | 13.85 | 24.06 | |
| CLIFNotation=CLIF, Backbone=Flan-T5-large2026.06 | 80 | 50 | 16.22 | |
| CLINGONotation=CLINGO, Backbone=Flan-T5-large2026.06 | 74.34 | 16.66 | 19.2 | |
| CGIFNotation=CGIF, Backbone=Flan-T5-large2026.06 | 69.1 | 20.83 | 16.92 | |
| FOLNotation=FOL, Backbone=Flan-T5-large2026.06 | 66.49 | 3.5 | 26.54 | |
| TFL+Notation=TFL+, Backbone=Flan-T5-large2026.06 | 58.11 | 10.41 | 16.91 |