Research

Paper

AI LLM February 27, 2026

The Subjectivity of Monoculture

Authors

Nathanael Jo, Nikhil Garg, Manish Raghavan

Abstract

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.

Metadata

arXiv ID: 2602.24086
Provider: ARXIV
Primary Category: cs.CY
Published: 2026-02-27
Fetched: 2026-03-02 06:04

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.24086v1</id>\n    <title>The Subjectivity of Monoculture</title>\n    <updated>2026-02-27T15:23:14Z</updated>\n    <link href='https://arxiv.org/abs/2602.24086v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.24086v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.\n  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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CY'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-02-27T15:23:14Z</published>\n    <arxiv:primary_category term='cs.CY'/>\n    <author>\n      <name>Nathanael Jo</name>\n    </author>\n    <author>\n      <name>Nikhil Garg</name>\n    </author>\n    <author>\n      <name>Manish Raghavan</name>\n    </author>\n  </entry>"
}