ACL 2025finding0 citations
EXECUTE: A Multilingual Benchmark for LLM Token Understanding
Lukas Edman, Helmut Schmid, Alexander Fraser
Abstract
The CUTE benchmark showed that LLMs struggle with character understanding in English. We extend it to more languages with diverse scripts and writing systems, introducing EXECUTE. Our simplified framework allows easy expansion to any language. Tests across multiple LLMs reveal that challenges in other languages are not always on the character level as in English. Some languages show word-level processing issues, some show no issues at all. We also examine sub-character tasks in Chinese, Japanese, and Korean to assess LLMs’ understanding of character components.
BibTeX
@inproceedings{edman-etal-2025-execute,
title = "{EXECUTE}: A Multilingual Benchmark for {LLM} Token Understanding",
author = "Edman, Lukas and
Schmid, Helmut and
Fraser, Alexander",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.95/",
doi = "10.18653/v1/2025.findings-acl.95",
pages = "1878--1887",
ISBN = "979-8-89176-256-5"
}