Chain-of-MetaWriting: Linguistic and Textual Analysis of How Small Language Models Write Young Students Texts

TL;DR

This paper presents Chain-of-MetaWriting, a method for analyzing multilingual Small Language Models' ability to imitate human writing processes like planning and evaluation, especially in educational contexts.

Contribution

It introduces a novel linguistic analysis framework that enables Small Language Models to mimic aspects of human writing, addressing gaps in meta-representation and communication learning.

Findings

SLMs struggle with sensitive topics like violence.

SLMs often use overly complex words for young audiences.

Text cohesion and coherence differ from human texts.

Abstract

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.