aiqbench analysis
This paper proposes "Co-Linguistics," a framework where Large Language Models act as co-scientists to formalize, compare, and generate linguistic theories rather than merely modeling human language ability. By leveraging program induction and active learning, AI can accelerate the derivation of empirical statements from axioms while humans retain central roles in conceptual evaluation and experimental design. This approach highlights a significant shift in how foundational scientific theories are constructed within linguistics through recursive AI-augmented cycles.
Co-Linguistics: AI-augmented Theory Construction in Linguistics
arXiv:2609.37635v1 Announce Type: new Abstract: LLMs have been studied in recent linguistics as potential models of humans' linguistic abilities. Here we discuss an entirely different use of AI, namely as a co-scientist, to help construct and assess linguistic theories (we refer to the result as "Co-Linguistics"). Since the 1960s, linguistics has developed theories that are in principle mathematically formalizable, often in the language of formal language theory or model theory. The AI revolution in mathematics will thus have consequences in linguistics-but with an essential twist: proving new theorems is rarely the linguist's goal. Rather, one seeks to find the best set of axioms to derive empirical statements. AI could accelerate research by making existing theories fully explicit, by comparing competing theories, and more ambitiously, by proposing new theories (in machine learning, this relates to "program induction"). It will also help assess theories by accelerating the identification and test of crucial predictions, thanks to unparalleled access to data (in machine learning, this relates to "active learning"). While the cycle from theory evaluation to theory construction may give rise to recursive and possibly autonomous improvement of linguistic theories, humans remain central: linguists provide scientific directions and evaluate theories conceptually, and experimental participants are needed to assess empirical predictions that are outside the reach of LLMs.
Abstract:LLMs have been studied in recent linguistics as potential models of humans' linguistic abilities. Here we discuss an entirely different use of AI, namely as a co-scientist, to help construct and assess linguistic theories (we refer to the result as "Co-Linguistics"). Since the 1960s, linguistics has developed theories that are in principle mathematically formalizable, often in the language of formal language theory or model theory. The AI revolution in mathematics will thus have consequences in linguistics-but with an essential twist: proving new theorems is rarely the linguist's goal. Rather, one seeks to find the best set of axioms to derive empirical statements. AI could accelerate research by making existing theories fully explicit, by comparing competing theories, and more ambitiously, by proposing new theories (in machine learning, this relates to "program induction"). It will also help assess theories by accelerating the identification and test of crucial predictions, thanks to unparalleled access to data (in machine learning, this relates to "active learning"). While the cycle from theory evaluation to theory construction may give rise to recursive and possibly autonomous improvement of linguistic theories, humans remain central: linguists provide scientific directions and evaluate theories conceptually, and experimental participants are needed to assess empirical predictions that are outside the reach of LLMs.
Computation and Language (cs.CL)
arXiv:2609.37635 [cs.CL]
(or arXiv:2609.37635v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.37635 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 303 words
Related coverage
When are safe Pareto improvements individually rational?
LessWrong · Oct 13, 2026
Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models
arXiv · Jul 29, 2026
CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing
arXiv · Jun 5, 2026
Causal Interventions Reveal Typologically Organized Syntactic Mechanisms in Multilingual Language Models
arXiv · Sep 1, 2026