LLM-based iterative personalization boosted electricity conservation by 0.56 kWh per room-day (18.3 percentage-point higher adjusted saving rate) versus text nudges in a three-arm field trial.
A large-scale replication of scenario-based experiments in psychology and management using large language models.Nature Computational Science, 5(8):627–634
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CY 2years
2026 2roles
background 2representative citing papers
LLMs reproduce observed attitudinal patterns in climate interventions reasonably well but diverge on causal effect estimates, with descriptive fit failing to predict causal accuracy across interventions and outcomes.
citing papers explorer
-
Enhancing behavioral nudges with large language model-based iterative personalization: A field experiment on electricity and hot-water conservation
LLM-based iterative personalization boosted electricity conservation by 0.56 kWh per room-day (18.3 percentage-point higher adjusted saving rate) versus text nudges in a three-arm field trial.
-
When simulations look right but causal effects go wrong: Large language models as behavioral simulators
LLMs reproduce observed attitudinal patterns in climate interventions reasonably well but diverge on causal effect estimates, with descriptive fit failing to predict causal accuracy across interventions and outcomes.