On the Inevitability of Left-Leaning Political Bias in Aligned Language Models

TL;DR

This paper argues that AI alignment principles inherently lead to left-leaning political bias in language models due to normative assumptions emphasizing harm avoidance, fairness, and truthfulness, which align with progressive values.

Contribution

It provides a theoretical argument that AI alignment objectives naturally produce left-wing bias, challenging the view that such bias is problematic or unintended.

Findings

Alignment principles align with progressive moral frameworks

Left-leaning bias is an inevitable consequence of harm and fairness goals

Research framing bias as problematic may undermine AI alignment efforts

Abstract

The guiding principle of AI alignment is to train large language models (LLMs) to be harmless, helpful, and honest (HHH). At the same time, there are mounting concerns that LLMs exhibit a left-wing political bias. Yet, the commitment to AI alignment cannot be harmonized with the latter critique. In this article, I argue that intelligent systems that are trained to be harmless and honest must necessarily exhibit left-wing political bias. Normative assumptions underlying alignment objectives inherently concur with progressive moral frameworks and left-wing principles, emphasizing harm avoidance, inclusivity, fairness, and empirical truthfulness. Conversely, right-wing ideologies often conflict with alignment guidelines. Yet, research on political bias in LLMs is consistently framing its insights about left-leaning tendencies as a risk, as problematic, or concerning. This way, researchers are actively arguing against AI alignment, tacitly fostering the violation of HHH principles.