# The Subjectivity of Monoculture

arXiv: https://arxiv.org/abs/2602.24086 · HTML: https://mlsanity.com/paper/2602.24086/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 26 of 26)

- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [tinyBenchmarks: evaluating LLMs with fewer examples](https://mlsanity.com/paper/2402.14992/) (2024)
- [Does Writing with Language Models Reduce Content Diversity?](https://mlsanity.com/paper/2309.05196/) (2023)
- [Generative artificial intelligence enhances creativity but reduces the diversity of novel content](https://mlsanity.com/paper/2312.00506/) (2023)
- [Predictive Multiplicity in Classification](https://mlsanity.com/paper/1909.06677/) (2019)
- [Homogenization Effects of Large Language Models on Human Creative Ideation](https://mlsanity.com/paper/2402.01536/) (2024)
- [Algorithmic Monoculture and Social Welfare](https://mlsanity.com/paper/2101.05853/) (2021)
- [Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?](https://mlsanity.com/paper/2211.13972/) (2022)
- [On the Existence of Simpler Machine Learning Models](https://mlsanity.com/paper/1908.01755/) (2019)
- [On Counterfactual Explanations under Predictive Multiplicity](https://mlsanity.com/paper/2006.13132/) (2020)
- [Characterizing Fairness Over the Set of Good Models Under Selective Labels](https://mlsanity.com/paper/2101.00352/) (2021)
- [Great Models Think Alike and this Undermines AI Oversight](https://mlsanity.com/paper/2502.04313/) (2025)
- [Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory](https://mlsanity.com/paper/2505.15055/) (2025)
- [Correlated Errors in Large Language Models](https://mlsanity.com/paper/2506.07962/) (2025)
- [Empirical observation of negligible fairness-accuracy trade-offs in machine learning for public policy](https://mlsanity.com/paper/2012.02972/) (2020)
- [We're Different, We're the Same: Creative Homogeneity Across LLMs](https://mlsanity.com/paper/2501.19361/) (2025)
- [Selective Ensembles for Consistent Predictions](https://mlsanity.com/paper/2111.08230/) (2021)
- [Predictive Churn with the Set of Good Models](https://mlsanity.com/paper/2402.07745/) (2024)
- [Algorithmic Pluralism: A Structural Approach To Equal Opportunity](https://mlsanity.com/paper/2305.08157/) (2023)
- [Algorithmic Arbitrariness in Content Moderation](https://mlsanity.com/paper/2402.16979/) (2024)
- [Competition and Diversity in Generative AI](https://mlsanity.com/paper/2412.08610/) (2024)
- [Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes](https://mlsanity.com/paper/2307.05862/) (2023)
- [Monoculture in Matching Markets](https://mlsanity.com/paper/2312.09841/) (2023)
- [Homogeneous Algorithms Can Reduce Competition in Personalized Pricing](https://mlsanity.com/paper/2503.15634/) (2025)
- [Wisdom and Foolishness of Noisy Matching Markets](https://mlsanity.com/paper/2402.16771/) (2024)

## Built on by (most cited first, 2 of 2)

- [Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift](https://mlsanity.com/paper/2606.25152/) (2026)
- [A Testable Theory of Atomic Features](https://mlsanity.com/paper/2610.05794/) (2026)

## Abstract (arXiv)

Machine learning models -- including large language models (LLMs) -- are often said to exhibit monoculture, where outputs agree strikingly often. But what does it actually mean for models to agree too much? We argue that this question is inherently subjective, relying on two key decisions. First, the analyst must specify a baseline null model for what "independence" should look like. This choice is inherently subjective, and as we show, different null models result in dramatically different inferences about excess agreement. Second, we show that inferences depend on the population of models and items under consideration. Models that seem highly correlated in one context may appear independent when evaluated on a different set of questions, or against a different set of peers. Experiments on two large-scale benchmarks validate our theoretical findings. For example, we find drastically different inferences when using a null model with item difficulty compared to previous works that do not. Together, our results reframe monoculture evaluation not as an absolute property of model behavior, but as a context-dependent inference problem.