Left Leaning Models: How AI Evaluates Economic Policy?

TL;DR

This study investigates AI models' preferences in economic policy evaluation, revealing a consistent bias towards growth, low unemployment, and inequality, with nuanced responses to context and quantitative changes.

Contribution

It systematically evaluates AI preferences in economic policy using conjoint experiments, uncovering consistent biases and sensitivity patterns across leading LLMs.

Findings

LLMs prefer high growth, low unemployment, and low inequality.

Preferences are sensitive to context but remain stable in monetary policy scenarios.

Reveals non-linear responses like loss aversion to quantitative changes.

Abstract

Would artificial intelligence (AI) cut interest rates or adopt conservative monetary policy? Would it deregulate or opt for a more controlled economy? As AI use by economic policymakers, academics, and market participants grows exponentially, it is becoming critical to understand AI preferences over economic policy. However, these preferences are not yet systematically evaluated and remain a black box. This paper makes a conjoint experiment on leading large language models (LLMs) from OpenAI, Anthropic, and Google, asking them to evaluate economic policy under multi-factor constraints. The results are remarkably consistent across models: most LLMs exhibit a strong preference for high growth, low unemployment, and low inequality over traditional macroeconomic concerns such as low inflation and low public debt. Scenario-specific experiments show that LLMs are sensitive to context but still display strong preferences for low unemployment and low inequality even in monetary-policy settings. Numerical sensitivity tests reveal intuitive responses to quantitative changes but also uncover non-linear patterns such as loss aversion.