On the Inevitability of Left-Leaning Political Bias in Aligned Language Models
This challenges the framing of political bias as a problem, suggesting it is inevitable for aligned AI, which could impact AI ethics and policy debates.
The paper argues that AI alignment objectives inherently lead to left-wing political bias in language models, as these goals align with progressive moral frameworks, while right-wing ideologies often conflict with them.
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.