ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline
This work addresses the challenge of computational creativity in language design for artists, philosophers, or enthusiasts, but it is incremental as it applies existing LLM methods to a new domain.
The paper tackled the problem of automating constructed language (conlang) creation by introducing ConlangCrafter, a multi-hop LLM pipeline that decomposes language design into modular stages, resulting in the generation of coherent and varied conlangs without human expertise, as demonstrated through metrics for consistency and typological diversity.
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 evaluate ConlangCrafter on metrics measuring consistency and typological diversity, demonstrating its ability to produce coherent and varied conlangs without human linguistic expertise.