ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Alper, Morris, Yanuka, Moran, Giryes, Raja, Beguš, Gašper
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917416212103168
author Alper, Morris
Yanuka, Moran
Giryes, Raja
Beguš, Gašper
author_facet Alper, Morris
Yanuka, Moran
Giryes, Raja
Beguš, Gašper
contents Constructed languages (conlangs) such as Esperanto and Quenya have played diverse roles in art, philosophy, and international communication. Meanwhile, foundation models have revolutionized creative generation in text, images, and beyond. In this work, we leverage modern LLMs as computational creativity aids for end-to-end conlang creation. We introduce ConlangCrafter, a multi-hop pipeline that decomposes language design into modular stages -- phonology, morphology, syntax, lexicon generation, and translation. At each stage, our method leverages LLMs' metalinguistic reasoning capabilities, injecting randomness to encourage diversity and leveraging self-refinement feedback to encourage consistency in the emerging language description. We construct a novel, scalable evaluation framework for this task, evaluating metrics measuring consistency and typological diversity. Automatic and manual evaluations demonstrate ConlangCrafter's ability to produce coherent and varied conlangs without human linguistic expertise.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06094
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline
Alper, Morris
Yanuka, Moran
Giryes, Raja
Beguš, Gašper
Computation and Language
Constructed languages (conlangs) such as Esperanto and Quenya have played diverse roles in art, philosophy, and international communication. Meanwhile, foundation models have revolutionized creative generation in text, images, and beyond. In this work, we leverage modern LLMs as computational creativity aids for end-to-end conlang creation. We introduce ConlangCrafter, a multi-hop pipeline that decomposes language design into modular stages -- phonology, morphology, syntax, lexicon generation, and translation. At each stage, our method leverages LLMs' metalinguistic reasoning capabilities, injecting randomness to encourage diversity and leveraging self-refinement feedback to encourage consistency in the emerging language description. We construct a novel, scalable evaluation framework for this task, evaluating metrics measuring consistency and typological diversity. Automatic and manual evaluations demonstrate ConlangCrafter's ability to produce coherent and varied conlangs without human linguistic expertise.
title ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline
topic Computation and Language
url https://arxiv.org/abs/2508.06094