Hypothesis Testing for Quantifying LLM-Human Misalignment in Multiple Choice Settings
By: Harbin Hong, Sebastian Caldas, Liu Leqi
Potential Business Impact:
Tests if computer brains copy people's choices.
As Large Language Models (LLMs) increasingly appear in social science research (e.g., economics and marketing), it becomes crucial to assess how well these models replicate human behavior. In this work, using hypothesis testing, we present a quantitative framework to assess the misalignment between LLM-simulated and actual human behaviors in multiple-choice survey settings. This framework allows us to determine in a principled way whether a specific language model can effectively simulate human opinions, decision-making, and general behaviors represented through multiple-choice options. We applied this framework to a popular language model for simulating people's opinions in various public surveys and found that this model is ill-suited for simulating the tested sub-populations (e.g., across different races, ages, and incomes) for contentious questions. This raises questions about the alignment of this language model with the tested populations, highlighting the need for new practices in using LLMs for social science studies beyond naive simulations of human subjects.
Similar Papers
Evaluating and Aligning Human Economic Risk Preferences in LLMs
General Economics
Makes AI make smarter money choices.
Should you use LLMs to simulate opinions? Quality checks for early-stage deliberation
Computers and Society
Tests if AI opinions are trustworthy for surveys.
Can Finetuing LLMs on Small Human Samples Increase Heterogeneity, Alignment, and Belief-Action Coherence?
Computation and Language
Makes computers act more like people in studies.