Communication Dans Un Congrès Année : 2025

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

Résumé

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 metarepresentation 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.
Fichier principal
Vignette du fichier
2412.14986v1.pdf (721) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04862740 , version 1 (03-01-2025)

Identifiants

Citer

Ioana Buhnila, Georgeta Cislaru, Amalia Todirascu. Chain-of-MetaWriting: Linguistic and Textual Analysis of How Small Language Models Write Young Students Texts. Proceedings of the First Workshop on Writing Aids at the Crossroads of AI, Cognitive Science and NLP (WRAICOGS 2025), co-located with COLING 2025, Michael Zock, Kentaro Inui, Zheng Yuan, Jan 2025, Abou Dhabi, United Arab Emirates. pp.1-15. ⟨hal-04862740⟩
10 Consultations
10 Téléchargements

Altmetric

Partager

More