-
A multilingual benchmark for evaluating metalinguistic knowledge WALS-Bench 1.0
This is a large-scale multilingual benchmark for evaluating metalinguistic knowledge (i.e. explicit knowledge about the structure of languages) in large language models using... -
Uniform Meaning Representation 2.0
The goal of the Uniform Meaning Representation (UMR) project is to design a meaning representation that can be used to annotate the semantic content of a text. UMR is primarily...
