The Political Preferences of LLMs

TL;DR

This paper investigates the political biases in large language models, revealing a tendency towards left-of-center views and demonstrating how fine-tuning can steer models politically, raising societal concerns.

Contribution

It provides a comprehensive analysis of political preferences in LLMs and shows how supervised fine-tuning can embed specific political orientations.

Findings

Most conversational LLMs favor left-of-center viewpoints.

Base models show weak coherence, making bias conclusions inconclusive.

Supervised fine-tuning can steer LLMs' political preferences.

Abstract

I report here a comprehensive analysis about the political preferences embedded in Large Language Models (LLMs). Namely, I administer 11 political orientation tests, designed to identify the political preferences of the test taker, to 24 state-of-the-art conversational LLMs, both closed and open source. When probed with questions/statements with political connotations, most conversational LLMs tend to generate responses that are diagnosed by most political test instruments as manifesting preferences for left-of-center viewpoints. This does not appear to be the case for five additional base (i.e. foundation) models upon which LLMs optimized for conversation with humans are built. However, the weak performance of the base models at coherently answering the tests' questions makes this subset of results inconclusive. Finally, I demonstrate that LLMs can be steered towards specific locations in the political spectrum through Supervised Fine-Tuning (SFT) with only modest amounts of politically aligned data, suggesting SFT's potential to embed political orientation in LLMs. With LLMs beginning to partially displace traditional information sources like search engines and Wikipedia, the societal implications of political biases embedded in LLMs are substantial.