Year: 2026
Type: article
Abstract: Climate policies often fail when they clash with cultural values, social identities, and fairness perceptions. We propose Acceptability-Constrained Climate Policy Design (ACCPD), using large language models as "cultural world models" to simulate public responses before implementation. By embedding LLMs in generative agent-based models and physical system simulators, ACCPD aims to enable policymakers to co-optimize for climate-policy efficacy and social legitimacy. We discuss methodological limitations regarding representation and LLM opacity.
Source: npj Climate Action
Institutions: University of Leeds, University of Exeter, University of Chicago, University of Graz, Central European University, University of Konstanz, Cranfield University, HafenCity University Hamburg, University of Lausanne, University of Zurich, Barcelona Supercomputing Center, RFF-CMCC European Institute on Economics and the Environment, CMCC Foundation - Euro-Mediterranean Center on Climate Change, Politecnico di Milano, University of Mannheim, Google DeepMind (United Kingdom)
Language: English
Subfield: Economics and Econometrics
Domain: Social Sciences
SDG: Climate action
Open Access status: gold
Estimated APC paid: $1,340
OpenAlex ID: W7140130684