Skip to main content

Danish Semantic Reasoning Benchmark

A Danish semantic reasoning benchmark compiled from lexical semantic resources This benchmark is the first version of a semantic reasoning benchmark for Danish compiled semi-automatically from a number of human-curated lexical-semantic resources, which function as our gold standard. The datasets constitute a benchmark for assessing selected language understanding capacities of large language models (LLMs) for Danish.

Beta version Current version is a beta version and is not yet fully curated. Compared to the first version, errors in the “lexical inference” dataset have been corrected.

License: Creative Commons Attribution-NoDerivs 4.0 International License

Data og ressourcer

Nøgleord

Yderligere info

URI https://data.gov.dk/dataset/lang/5b6dd13e-2035-4238-a9bf-fc6a60523cf0
Destinationsside https://github.com/kuhumcst/danish-semantic-reasoning-benchmark
Høstes af Datavejviser Ja
Udgivelsesdato 18-11-2024
Seneste ændringsdato 22-11-2024
Opdateringsfrekvens kontinuerlig
Dækningsperiode  / 
Emne(r)
  • 16.05.07 Sprog og retskrivning
  • Regeringen og den offentlige sektor
Adgangsrettigheder offentlig
Overholder
Proveniensudsagn
Dokumentation