Chain-of-MetaWriting: Linguistic and Textual Analysis of How Small Language Models Write Young Students Texts
This addresses the problem of using SLMs for educational writing tasks for young students, but it is incremental as it builds on existing linguistic analysis methods.
The paper analyzed how small language models (SLMs) write texts for young students, using a method called Chain-of-MetaWriting to imitate human writing steps like planning and evaluation, and found that SLMs struggle with sensitive topics and use overly complex words, differing from human texts in cohesion and coherence.
Large Language Models (LLMs) have been used to generate texts in response to different writing tasks: reports, essays, story telling. However, language models do not have a meta-representation of the text writing process, nor inherent communication learning needs, comparable to those of young human students. This paper introduces a fine-grained linguistic and textual analysis of multilingual Small Language Models' (SLMs) writing. With our method, Chain-of-MetaWriting, SLMs can imitate some steps of the human writing process, such as planning and evaluation. We mainly focused on short story and essay writing tasks in French for schoolchildren and undergraduate students respectively. Our results show that SLMs encounter difficulties in assisting young students on sensitive topics such as violence in the schoolyard, and they sometimes use words too complex for the target audience. In particular, the output is quite different from the human produced texts in term of text cohesion and coherence regarding temporal connectors, topic progression, reference.