arXiv Machine Learning July 24, 2026 By Messi H. J. Lee

How Robust Is Homogeneity Bias in LLMs? Evidence Across Models, Decoding Settings, and Identity Signals

Read the original on arXiv Machine Learning →

arXiv:2501. 02211v3 Announce Type: replace-cross Abstract: Large language models (LLMs) reproduce homogeneity bias -- the tendency to portray marginalized groups as more internally similar than dominant groups -- but whether this bias generalizes across models, is stable under different inference settings, or depends on how group identity is signaled remains unstudied.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 25

Homogeneity Bias in Open-Weight LLMs Is Robust to Decoding Hyperparameters

arXiv:2501. 02211v2 Announce Type: replace-cross Abstract: Large language models (LLMs) reproduce homogeneity bias -- the tendency to portray marginalized groups as more internally similar than dominant groups -- but whether this bias is stable or an artifact of inference settings has only been studied in single proprietary models.

By Messi H. J. Lee

llms safety

arXiv AI

6d ago

Large Language Models Reproduce Racial Stereotypes When Used for Text Annotation

arXiv:2603. 13891v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for automated text annotation in tasks ranging from academic research to content moderation and hiring.

By Petter T\"ornberg

llms fine-tuning safety

arXiv AI

Jul 24

ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues

arXiv:2604. 01925v2 Announce Type: replace-cross Abstract: Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity is conveyed indirectly.

By Bhaskara Hanuma Vedula, Darshan Anghan, Ishita Goyal, Ponnurangam Kumaraguru, Abhijnan Chakraborty

llms benchmarks safety

arXiv AI

Jun 3

Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupations

arXiv:2510. 21011v3 Announce Type: replace-cross Abstract: As generative AI tools are increasingly used to portray people in professional roles, understanding their racial and gender representational biases is critical.

By Ilona van der Linden, Sahana Kumar, Arnav Dixit, Aadi Sudan, Smruthi Danda, David C. Anastasiu, Kai Lukoff

llms safety

Hugging Face Trending Papers

Jun 17

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.

llms benchmarks safety

arXiv Machine Learning

Jul 31

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations

arXiv:2607. 28319v1 Announce Type: cross Abstract: This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs).

By Pere Martra, Eugenio Mart\'inez C\'amara, Alfonso Ure\~na L\'opez

llms efficiency benchmarks safety

Related stories

Homogeneity Bias in Open-Weight LLMs Is Robust to Decoding Hyperparameters

Large Language Models Reproduce Racial Stereotypes When Used for Text Annotation

ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues

Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupations

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations