Metraipolis › archive › dc_dc42e501fef2

Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculture — arXiv:2609.35302

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.35302
License (as archived): CC0-1.0
Archived: 2026-10-07T20:58:42.232Z
SHA-256 of the archived text: eaf715197305e6349aad9948a4ff6435f05623f4746087ac8223d1574a0b6953
Stable URL of this page: https://metraipolis.com/documento/dc_dc42e501fef2

How to cite

Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculture — arXiv:2609.35302 — arXiv (en), https://arxiv.org/abs/2609.35302 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc42e501fef2 (Metraipolis archive dc_dc42e501fef2, sha256 eaf715197305e6349aad9948a4ff6435f05623f4746087ac8223d1574a0b6953)

BibTeX

@misc{dcdc42e501fef2,
  title = {Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculture — arXiv:2609.35302},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35302},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc42e501fef2; sha256 eaf715197305e6349aad9948a4ff6435f05623f4746087ac8223d1574a0b6953},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35302. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 \textit{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. Data and Code are accessible \href{ this https URL }{here}.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.35302 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:01.833Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).