Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculture

As Large Language Models (LLMs) become central to how we access and share information, they play an increasingly powerful role in shaping global knowledge. However, as these models evolve, their outputs risk converging into a generative monoculture, where the diversity of perspectives they represent narrows over time. Studies at the model level often fail to pinpoint which specific topics or viewpoints are being marginalised or amplified in this process. In this paper, we introduce a method to measure shifts in topic saliency across model families, tracking what gains or loses prominence during post-training. Applying this approach to a case study of climate change discourse, we demonstrate how homogenisation affects the representation of diverse solutions across different models. We also test interventions to counter this trend, showing that specialised models can help preserve a broader range of perspectives. This underscores the importance of monitoring topic saliency to diagnose the risks of monoculture and to ensure AI systems reflect a pluralism of ideas.

Recommended citation: Peter, O., Simperl E. & Devlin, K. (2025). Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculture. In Findings of the Association for Computational Linguistics: EMNLP 2026
Download Paper