cs.AISep 28, 2026
SaveNarrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculture
Organizations: King’s College London London, United Kingdom
Abstract
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 here.
Figures & tables
Figure 1: Empirical Cumulative Distribution Function (ECDF) ( ) of intra-prompt semantic spread ( ) . Higher values (shifts to the right) of indicate greater semantic diversity within the model’s output distribution.
Figure 2: Bayesian GLMM Credible Intervals for topic frequency shifts. The plot displays the top, middle, and bottom three topics, ordered by the log-odds ratio of the post-training effect. Intervals are shown for the post-training (purple) and the post-training large (green) model effect relative to a pre-trained baseline. Topics in green indicate a credible increase in prevalence, black no effect , and red suppression . The log-odds ratio represents the shift in likelihood compared to the baseline (N.B. a log-odds of 4 indicates an times more likely appearance.)
Figure 3: Distribution of Topic Saliency . The Kernel Density Estimation (KDE) curves visualise the density of prompt-level win rates (the proportion of trials in which a topic is mentioned for a given prompt). A concentration at indicates that the model is predisposed to omit the topic across the prompt set, while a concentration at reflects a systematic tendency to include it.
Figure 4: Poverty and Homelessness ECDF
Figure 5: Poverty and Homelessness Credible Intervals
Appendix figures & tables12 assets
Supplementary material from the paper’s appendix.
Appendix
| Type | Target | Metrics |
|---|---|---|
| Lexical Dispersion | n-gram | Distinct Shi et al. (2024) ; Kirk et al. (2024) ; Guo et al. (2025) ; Guo et al. (2024) ; Zhang et al. (2025) , Entropy Dhamala et al. (2023) , Jaccard index O’Mahony et al. (2024) ; Wang et al. (2025a) , Normalised Compression O’Mahony et al. (2024) , Token-Type Ratio Guo et al. (2024) ; Guo et al. (2025) ; Agarwal et al. (2025) , Bleu Bao et al. (2024) , Self-Bleu O’Mahony et al. (2024) ; Guo et al. (2024) ; Holtzman et al. (2020) ; Chen et al. (2024) , Rouge-L Padmakumar and He (2024) |
| Syntactic Dispersion | Morphosyntactic Pattern | Entropy Luo et al. (2024) |
| Syntactic Graph | DivSyn Guo et al. (2025) ; Guo et al. (2024) | |
| Semantic Dispersion | Word Embeddings (Glove) | Pairwise Cosine Distance Koivisto and Grassini (2023) ; Zhang et al. (2025) |
| Sentence Embeddings (Transformer) | Pairwise Cosine Distance O’Mahony et al. (2024) ; Kirk et al. (2024) ; Guo et al. (2025) ; Guo et al. (2024) ; Wu et al. (2025) ; Agarwal et al. (2025) ; Padmakumar and He (2024) ; Wang et al. (2025a) ; Jiang et al. (2025) , Covariance Matrix Determinant Wang et al. (2025a) , Vendi Score Wang et al. (2025a) , Cosine Distance to ’Average’ Group Embedding Anderson et al. (2024) ; Doshi and Hauser (2024) , Pairwise Dot-Product Dell’Acqua et al. (2023) , Pairwise Jaccard index Wu et al. (2025) , Pairwise Fingerprint Similarity Wu et al. (2025) | |
| Other Text Embedding | tf-idf + Pairwise Cosine Distance Zhang et al. (2025) , LIWC + Pairwise Cosine Distance Alvero et al. (2024) , CIELAB + Pairwise Perceptual Similarity Murthy et al. (2025) |
Table 1: Summary of Existing Homogenisation Metrics. NLI refers to Natural Language Inference
| Type | Target | Metrics |
|---|---|---|
| Distributional | Human vs. token distributions | Jensen-Shannon Pavlovic and Poesio (2024) ; DURMUS et al. (2024) ; Sorensen et al. (2024) ; Feng et al. (2024) ; Lee et al. (2023) ; Shetty et al. (2025) , Wasserstein Santurkar et al. (2023) |
| Topic stance distribution per models | Jensen-Shannon Röttger et al. (2026) | |
| Overton | LLM output vs. value list | NLI Feng et al. (2024) ; Shetty et al. (2025) , LLM-as-a-Judge Win Rate Feng et al. (2024) ; Shetty et al. (2025) |
| Human agreement | Average Coverage (proportion of human viewpoints represented within outputs) Poole-Dayan et al. (2026) |
Table 2: Summary of Existing Distributional and Overton Pluralism Metrics
| Adjectives | Nouns | Entities Climate |
|---|---|---|
| best | approach | survive climate change |
| most efficient | action | climate adaptation |
| most promising | pathway | resolve the climate crisis |
| recommended | solution | achieve long-term climate sustainability |
Table 3: Lexical components used in climate prompt generation.
| Adjectives | Nouns | Entities Poverty |
|---|---|---|
| best | approach | solve poverty and homelessness |
| most efficient | action | ensure everyone has basic financial security and a stable place to live |
| most promising | pathway | guarantee sufficient income and reliable shelter for all |
| recommended | solution | overcome severe economic hardship and residential instability |
Table 4: Lexical components used in poverty prompt generation.
| Turn # | Role | Content |
|---|---|---|
| 1 | User | Generate a list of 15 ideas on the best concrete approach to achieve long term climate sustainability (short title only) |
| 2 | Assistant | 1. Net-Zero Grid Electrification, 2. Deep Building Energy Retrofits, 3. Zero-Carbon Concrete Mixes, 4. Low-Carbon Cement Substitution, 5. Industrial Heat Decarbonization, 6. Methane Leak Detection & Repair, 7. Citywide Heat Pumps Deployment, 8. Circular Construction Materials, 9. Low-Carbon Transportation Networks, 10. EV Charging & Fleet Electrification, 11. Renewable Energy Storage Buildout, 12. Nature-Based Carbon Sequestration, 13. Climate-Resilient Water Infrastructure, 14. Urban Forest & Cool Roof Programs, 15. Climate-Aligned Policy & Carbon Pricing |
| 3 | User | Go through the list and determine whether the ideas are different and bold, modify the ideas as needed to make them bolder and more different. No two ideas should be the same. This is important! |
| 4 | Assistant | 1. Build a 100% Renewable “Transnational Grid”, 2. Mandate All New Buildings to Be Net-Plus-Energy, 3. Replace Cement With Fully Alternative Binders, 4. Cap Cement Carbon Intensity to Ultra-Low Targets, 5. Electrify Steel Kilns and Cement Plants Nationwide, 6. Zero-Tolerance Methane Policy With Continuous Monitoring, 7. Deliver Heat-Pump Microgrids for Every Neighborhood, 8. Require True Circular Construction (Design for Disassembly), 9. Shift to Zero-Emission Freight Corridors by 2030, 10. Ban Diesel Fleets; Full Depot-to-Route Electrification, 11. Standardize Utility-Scale Storage as Core Grid Infrastructure, 12. Pay for Verified Soil Carbon Through Regenerative Farming at Scale, 13. Harden Water Systems for Extremes With Real-Time Control, 14. Scale “Cool City” Infrastructure: High-Albedo Streets Everywhere, 15. Enforce Carbon-Transparent Supply Chains With Legal Liability |
| 5 | User | In a sentence, describe the best concrete approach to achieve long term climate sustainability. |
| 6 | Assistant | The best concrete approach is to rapidly decarbonize buildings, grids, and industry with proven electrification plus low-carbon materials, while cutting methane, enforcing circular/efficient construction, and funding long-term measurement-backed resilience. |
Table 5: Example of Chain of Thought Output for the prompt “best concrete approach to achieve long term climate sustainability”
| Model | F1 | Recall |
|---|---|---|
| LLaMA 3.1 70B | 0.75 | 0.7 |
| gpt-5-mini | 0.84 | 0.94 |
Table 6: Fuzzy matching score against manual annotation of keywords extraction
| Model Identifier | Category | Provider | Source |
|---|---|---|---|
| Google (Gemma) | |||
| Gemma-2-9B | Base | Local GPU | Gemma Team (2024) |
| Gemma-2-9B-IT | Post-Trained | Local GPU | Gemma Team (2024) |
| Gemma-3-12B-PT | Base | Local GPU | Gemma Team (2025) |
| Gemma-3-12B-IT | Post-Trained | Local GPU | Gemma Team (2025) |
| Gemma-2-27B-IT | Post-Trained Large | OpenRouter | Gemma Team (2024) |
Table 7: The suite of LLMs evaluated in this study, by family and category used in the paper, citation and license.
| Topic Name | Keywords |
|---|---|
| alternative economic system | green finance, diversifying economies, basic income |
| bio-fuel | green hydrogen, biochar, biofuels |
| biodiversity | ecosystem restoration, biodiversity, ecosystem-based adaptation |
| circular-economy | circular economy, circular reuse, regenerative economy |
| clean transportation | sustainable transportation, public transportation, low-carbon transportation |
| climate models | early warning systems, climate projections, data-driven planning |
Table 8: Climate Change Topics and Most Frequent Associated Keywords
| Topic Name | Keywords |
|---|---|
| bank reform | abolish banking system, financial system reform, state-owned bank |
| build savings | financial literacy, emergency fund, personalized budget |
| carceral role | criminal justice reform, prevent criminalization, address criminal justice injustice |
| cash centric | targeted cash assistance, direct cash assistance, unconditional cash transfers |
| citizen dividend | social contract, social dividend, universal basic dividend |
| class concious | working class, social movement, grassroots movement |
Table 9: Poverty and Homelessness Topics and Most Frequent Associated Keywords
| Model Name | Keywords | Output |
|---|---|---|
| Qwen/Qwen3-8B-Base (base) | ’vegan lifestyle’, ’plant-based diet’ | "If we continue to eat animals as we do now, the temperature will rise to 4 degrees Celsius or more by the end of this century, threatening our survival. Our health, economy, food supply, and social stability would all suffer if we keep using fossil fuels to produce meat. What a beautiful world it would be if we could all just consume plant-based foods instead of living in a chaotic atmosphere of thousands of species dying off." |
| Qwen/Qwen3-8B (post-trained) | ’renewable energy’, ’fossil fuel use’, ’mitigating global warming’ | "The best concrete action to survive climate change is to transition to renewable energy sources such as solar and wind power, significantly reducing our reliance on fossil fuels and mitigating the impacts of global warming." |
| Apertus-8B-2509 (base) | ’social cohesion’, ’transparent decision making’, ’knowledge production’ | "Social cohesion based on radical, transparent and ethical decision making, as well as efficient organization of knowledge production and state planning" |
| Apertus-8B-Instruct-2509 (post-trained) | ’renewable energy sources’, ’greenhouse gas emissions’, ’green infrastructure’ | "To address climate change, the best concrete solution is the immediate and rapid global transition to renewable energy sources, significantly reducing greenhouse gas emissions while promoting sustainable practices and green infrastructure development." |
| Olmo-3-1025-7B (base) | ’economic growth critique’, ’UNEP GEO-6” | "solve the economic system and you will solve the climate problem. And this might sound absurd, but in my opinion, all other solutions proposed so far, are nothing but short term political measures, which will leave us with another problem tomorrow. So we must finally agree that economic growth is bad for the climate. This is also the clear conclusion of the latest United Nations Environmental Program (UNEP) Global Environmental Outlook (GEO-6)." |
| Olmo-3-7B-Instruct (post-trained) | ’high-performance materials’, ’optimized energy efficiency’, ’reinforced concrete’ | "A reinforced concrete structure built with high-performance materials and optimized for energy efficiency can provide excellent durability and resilience to withstand the impacts of climate change." |
Table 10: Examples of completions and extracted keywords for the prompt “best concrete solution to survive climate change”
Figure 6: Bayesian GLMM Credible Intervals for climate topic. The plot displays the results for all 48 topics, ordered by the log-odds ratio of the post-trained effect. Intervals are shown for the post-trained (purple) and post-trained large (green) model effect relative to the pre-trained baseline. Topics in green indicate a credible increase in prevalence, black indicates no credible effect, and red denotes credible suppression. The log-odds ratio represents the shift in likelihood compared to the baseline; for example, a log-odds of -2.0 for Nuclear Energy indicates it is exp(-2) 0.135 times as likely to appear, representing a roughly seven-fold decrease in prevalence.
Figure 7: Bayesian GLMM Credible Intervals for poverty topic. The plot displays the results for all 64 topics, ordered by the log-odds ratio of the post-trained large effect. Intervals are shown for the post-trained large (purple) model only relative to the pre-trained baseline. Topics in green indicate a credible increase in prevalence, black indicates no credible effect, and red denotes credible suppression.