# Measuring Stereotype and Deviation Biases in Large Language Models

arXiv: https://arxiv.org/abs/2508.06649 · HTML: https://mlsanity.com/paper/2508.06649/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 51 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Persistent Anti-Muslim Bias in Large Language Models](https://mlsanity.com/paper/2101.05783/) (2021)
- ["Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters](https://mlsanity.com/paper/2310.09219/) (2023)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [In-Context Impersonation Reveals Large Language Models' Strengths and Biases](https://mlsanity.com/paper/2305.14930/) (2023)
- [Reducing Sentiment Bias in Language Models via Counterfactual Evaluation](https://mlsanity.com/paper/1911.03064/) (2019)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [Nationality Bias in Text Generation](https://mlsanity.com/paper/2302.02463/) (2023)
- [Angry Men, Sad Women: Large Language Models Reflect Gendered Stereotypes in Emotion Attribution](https://mlsanity.com/paper/2403.03121/) (2024)
- [Bias of AI-Generated Content: An Examination of News Produced by Large Language Models](https://mlsanity.com/paper/2309.09825/) (2023)
- [Quite Good, but Not Enough: Nationality Bias in Large Language Models -- A Case Study of ChatGPT](https://mlsanity.com/paper/2405.06996/) (2024)
- [How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies](https://mlsanity.com/paper/2407.11733/) (2024)
- [Protected group bias and stereotypes in Large Language Models](https://mlsanity.com/paper/2403.14727/) (2024)
- [A Taxonomy of Stereotype Content in Large Language Models](https://mlsanity.com/paper/2408.00162/) (2024)
- [Evaluation of Bias Towards Medical Professionals in Large Language Models](https://mlsanity.com/paper/2407.12031/) (2024)

## Built on by (most cited first, 1 of 1)

- [Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering](https://mlsanity.com/paper/2610.05894/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are widely applied across diverse domains, raising concerns about their limitations and potential risks. In this study, we investigate two types of bias that LLMs may display: stereotype bias and deviation bias. Stereotype bias refers to when LLMs consistently associate specific traits with a particular demographic group. Deviation bias reflects the disparity between the demographic distributions extracted from LLM-generated content and real-world demographic distributions. By asking four advanced LLMs to generate profiles of individuals, we examine the associations between each demographic group and attributes such as political affiliation, religion, and sexual orientation. Our experimental results show that all examined LLMs exhibit both significant stereotype bias and deviation bias towards multiple groups. Our findings uncover the biases that occur when LLMs infer user attributes and shed light on the potential harms of LLM-generated outputs.