# Diminished Diversity-of-Thought in a Standard Large Language Model

arXiv: https://arxiv.org/abs/2302.07267 · HTML: https://mlsanity.com/paper/2302.07267/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 9 of its 76 references that are in the map.
- First posted on arXiv 13 Feb 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 9 of 9)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [Who is GPT-3? An Exploration of Personality, Values and Demographics](https://mlsanity.com/paper/2209.14338/) (2022)
- [Algorithmic Amplification of Politics on Twitter](https://mlsanity.com/paper/2110.11010/) (2021)
- [Differentially Private Natural Language Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2301.09112/) (2023)

## Built on by (most cited first, 30 of 45)

- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [The Political Preferences of LLMs](https://mlsanity.com/paper/2402.01789/) (2024)
- [Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy](https://mlsanity.com/paper/2402.19379/) (2024)
- [Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions](https://mlsanity.com/paper/2502.16761/) (2025)
- [Benchmarking Distributional Alignment of Large Language Models](https://mlsanity.com/paper/2411.05403/) (2024)
- [SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors](https://mlsanity.com/paper/2510.17516/) (2025)
- [Virtual Personas for Language Models via an Anthology of Backstories](https://mlsanity.com/paper/2407.06576/) (2024)
- [The Homogenizing Effect of Large Language Models on Human Expression and Thought](https://mlsanity.com/paper/2508.01491/) (2025)
- [This human study did not involve human subjects: Validating LLM simulations as behavioral evidence](https://mlsanity.com/paper/2602.15785/) (2026)
- [Empirical evidence of Large Language Model's influence on human spoken communication](https://mlsanity.com/paper/2409.01754/) (2024)
- [LLM-GLOBE: A Benchmark Evaluating the Cultural Values Embedded in LLM Output](https://mlsanity.com/paper/2411.06032/) (2024)
- [Diverse Preference Learning for Capabilities and Alignment](https://mlsanity.com/paper/2511.08594/) (2025)
- [Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament](https://mlsanity.com/paper/2310.13014/) (2023)
- [AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy](https://mlsanity.com/paper/2402.07862/) (2024)
- [ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs](https://mlsanity.com/paper/2409.09586/) (2024)
- [Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework](https://mlsanity.com/paper/2412.06681/) (2024)
- [Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Review](https://mlsanity.com/paper/2401.01519/) (2024)
- [The threat of analytic flexibility in using large language models to simulate human data](https://mlsanity.com/paper/2509.13397/) (2025)
- [Studying and improving reasoning in humans and machines](https://mlsanity.com/paper/2309.12485/) (2023)
- [SaudiCulture: A Benchmark for Evaluating Large Language Models Cultural Competence within Saudi Arabia](https://mlsanity.com/paper/2503.17485/) (2025)
- [Doubly-Robust LLM-as-a-Judge: Externally Valid Estimation with Imperfect Personas](https://mlsanity.com/paper/2509.22957/) (2025)
- [Aligning LLM with human travel choices: a persona-based embedding learning approach](https://mlsanity.com/paper/2505.19003/) (2025)
- [Large Language Models as Psychological Simulators: A Methodological Guide](https://mlsanity.com/paper/2506.16702/) (2025)
- [Cognitive models can reveal interpretable value trade-offs in language models](https://mlsanity.com/paper/2506.20666/) (2025)
- [AI Agents Alone Are Not (Yet) Sufficient for Social Simulation](https://mlsanity.com/paper/2603.00113/) (2026)
- [The creative psychometric item generator: a framework for item generation and validation using large language models](https://mlsanity.com/paper/2409.00202/) (2024)
- [Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering](https://mlsanity.com/paper/2601.22010/) (2026)
- [Parametric Social Identity Injection and Diversification in Public Opinion Simulation](https://mlsanity.com/paper/2603.16142/) (2026)
- [Persona-Based Simulation of Human Opinion at Population Scale](https://mlsanity.com/paper/2603.27056/) (2026)

## Abstract (arXiv)

We test whether Large Language Models (LLMs) can be used to simulate human participants in social-science studies. To do this, we run replications of 14 studies from the Many Labs 2 replication project with OpenAI's text-davinci-003 model, colloquially known as GPT3.5. Based on our pre-registered analyses, we find that among the eight studies we could analyse, our GPT sample replicated 37.5% of the original results and 37.5% of the Many Labs 2 results. However, we were unable to analyse the remaining six studies due to an unexpected phenomenon we call the "correct answer" effect. Different runs of GPT3.5 answered nuanced questions probing political orientation, economic preference, judgement, and moral philosophy with zero or near-zero variation in responses: with the supposedly "correct answer." In one exploratory follow-up study, we found that a "correct answer" was robust to changing the demographic details that precede the prompt. In another, we found that most but not all "correct answers" were robust to changing the order of answer choices. One of our most striking findings occurred in our replication of the Moral Foundations Theory survey results, where we found GPT3.5 identifying as a political conservative in 99.6% of the cases, and as a liberal in 99.3% of the cases in the reverse-order condition. However, both self-reported 'GPT conservatives' and 'GPT liberals' showed right-leaning moral foundations. Our results cast doubts on the validity of using LLMs as a general replacement for human participants in the social sciences. Our results also raise concerns that a hypothetical AI-led future may be subject to a diminished diversity-of-thought.