CLDec 13, 2025
Large language models have learned to use language
arXiv:2512.12447v1
Originality Synthesis-oriented
AI Analysis
This is an incremental perspective shift for researchers in linguistics and AI, focusing on re-evaluating language knowledge assessment.
The paper argues that recognizing large language models' ability to use language can lead to breakthroughs in language science, requiring a shift away from traditional evaluation methods like the Turing test.
Acknowledging that large language models have learned to use language can open doors to breakthrough language science. Achieving these breakthroughs may require abandoning some long-held ideas about how language knowledge is evaluated and reckoning with the difficult fact that we have entered a post-Turing test era.