Large pre-trained neural models have achieved remarkable success in natural language process (NLP), inspiring a growing body of research analyzing their ability from different aspects. In this paper, we propose a test suite to evaluate the cohesive ability of pre-trained language models. The test suite contains multiple cohesion phenomena between adjacent and non-adjacent sentences. We try to compare different pre-trained language models on these phenomena and analyze the experimental results,hoping more attention can be given to discourse cohesion in the future.
@article{arxiv.2503.06137,
title = {Evaluating Discourse Cohesion in Pre-trained Language Models},
author = {Jie He and Wanqiu Long and Deyi Xiong},
journal= {arXiv preprint arXiv:2503.06137},
year = {2025}
}