Inertia in Moral and Value Judgments of Large Language Models

ArXi:2408.09049v3 Announce Type: replace Large Language Models (LLMs) behave non-deterministically, and prompting has become a common method for steering their outputs. A popular strategy is to assign a persona to the model to produce varied, context-sensitive responses, similar to how responses vary across human individuals. Against the expectation that persona prompting yields a wide range of opinions, our experiments show that LLMs keep consistent value orientations.