A multi-step 'infer ideology, then vote' prompt reduced weighted absolute error to 5.24% (2020, 21 states) and 3.49% (2024, 11 battleground states) versus 14.97-25.96% for single-step prompts, while residual political and demographic biases persisted.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Large-Scale Simulation on Large Language Models for Decision-Making in Political Science
A multi-step 'infer ideology, then vote' prompt reduced weighted absolute error to 5.24% (2020, 21 states) and 3.49% (2024, 11 battleground states) versus 14.97-25.96% for single-step prompts, while residual political and demographic biases persisted.