Previous evaluations of large language models (LLMs) focused on the perspective of various tasks or abilities. In this paper, we propose to evaluate from a linguistic viewpoint and argue that morpheme, a potential linguistic feature that captures both word-formation and lexical semantics, is another suitable component for evaluation that remains largely unexplored. In light of this, we construct MorphEval, a morpheme-informed benchmark, including three datasets following the bottom-up levels of characters, words, and sentences in Chinese, and then evaluate representative LLMs with both zero- and few-shot settings under two metrics. From this perspective, we reveal three aspects of issues LLMs nowadays encounter: dysfunctions in morphology and syntax, challenges with the long-tailed distribution of semantics, and difficulties from cultural implications. In these scenarios, even a smaller Chinese-targeted model may outperform ChatGPT, highlighting the actual challenges LLMs face and the necessity of language-specific improvements when applied to non-English languages. This new approach could also help guide model enhancements as well as get extended to other languages.

Morphemes serve as a strong linguistic feature to capture lexical semantics, with higher coverage than words and more natural than sememes. However, due to the lack of morpheme-informed resources and the expense of manual annotation, morpheme-enhanced methods remain largely unexplored in Computational Linguistics. To address this issue, we propose the task of Morpheme Sense Disambiguation (MSD), with two subtasks in-text and in-word, similar to Word Sense Disambiguation (WSD) and Sememe Prediction (SP), to generalize morpheme features on more tasks. We first build the MorDis resource for Chinese, including MorInv as a morpheme inventory, MorTxt and MorWrd as two types of morpheme-annotated datasets. Next, we provide two baselines in each evaluation; the best model yields a promising precision of 77.66% on in-text MSD and 88.19% on in-word MSD, indicating its comparability with WSD and superiority over SP. Finally, we demonstrate that predicted morphemes achieve comparable performance with the ground-truth ones on a downstream application of Definition Generation (DG). This validates the feasibility and applicability of our proposed tasks. The resources and workflow of MSD will provide new insights and solutions for downstream tasks, including DG as well as WSD, training pre-trained models, etc.