Andreas Waldis, Yotam Perlitz, Leshem Choshen, Yufang Hou 0001, Iryna Gurevych. Holmes ⌕ A Benchmark to Assess the Linguistic Competence of Language Models. TACL, 12:1616-1647, 2024. [doi]
@article{WaldisWPCCHG24a,
title = {Holmes ⌕ A Benchmark to Assess the Linguistic Competence of Language Models},
author = {Andreas Waldis and Yotam Perlitz and Leshem Choshen and Yufang Hou 0001 and Iryna Gurevych},
year = {2024},
doi = {10.1162/tacl_a_00718},
url = {https://doi.org/10.1162/tacl_a_00718},
researchr = {https://researchr.org/publication/WaldisWPCCHG24a},
cites = {0},
citedby = {0},
journal = {TACL},
volume = {12},
pages = {1616-1647},
}