FOLIO-KR

FOLIO-KR (FOLIO Knowledge Representation) is a dataset generated from the original FOLIO dataset spanning several KR notations from First-Order Logic (FOL).

The gold train, test and valid splits are provided. It is the dataset used in "Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering".

Notations

The dataset currently supports the following KR notations:

• Common Logic Interchange Format (CLIF)
• Concept Graph Interchange Format (CGIF)
• CLINGO
• Tensor Function Logic (TFL+)
• Custom languages (e.g. MINIFOL2)

References

• Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering
• SEF-CLGC at SemEval-2026 Task 11: Logical Notation Impact on Language Model Performance