Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity
This reveals a bias issue in LLMs that could affect users in political or ethical contexts, though it is incremental in exploring social biases.
The study found that large language models (LLMs) like GPT-3/3.5 and OPT reproduce moral biases tied to political identities, generating text that aligns with liberal or conservative prompts, as measured using Moral Foundations Theory.
Large Language Models (LLMs) have demonstrated impressive capabilities in generating fluent text, as well as tendencies to reproduce undesirable social biases. This study investigates whether LLMs reproduce the moral biases associated with political groups in the United States, an instance of a broader capability herein termed moral mimicry. This hypothesis is explored in the GPT-3/3.5 and OPT families of Transformer-based LLMs. Using tools from Moral Foundations Theory, it is shown that these LLMs are indeed moral mimics. When prompted with a liberal or conservative political identity, the models generate text reflecting corresponding moral biases. This study also explores the relationship between moral mimicry and model size, and similarity between human and LLM moral word use.