Multilingual Sentence Embeddings for Linguistic-Integrated Reliability Audit
Computation and Language
2026-07-20 v1 Artificial Intelligence
Abstract
Multilingual assessment systems commonly rely on translation for scoring and quality-control processes. We evaluate whether multilingual sentence embeddings can replace translated English input for Linguistic-Integrated Reliability Auditing (LiRA) across 11 PIRLS constructed-response items and three embedding models. Native-language embeddings reproduced translation-based reliability estimates closely while recovering responses excluded after translation failure, with no meaningful change in reliability.
Cite
@article{arxiv.2607.17466,
title = {Multilingual Sentence Embeddings for Linguistic-Integrated Reliability Audit},
author = {Ummugul Bezirhan and Ji Yoon Jung and Matthias von Davier},
journal= {arXiv preprint arXiv:2607.17466},
year = {2026}
}