arXiv Computation and Language October 22, 2026 By Hazel Chen, Peter West, Hila Gonen

Guilt by Association: Semantic Leakage Drives Associative Gender Bias

Read the original on arXiv Computation and Language →

The paper investigates semantic leakage, where a concept in a prompt influences model output about an entity even when the concept is unrelated, and shows that this effect persists even when the concept is not directly attributed to the entity. Extending this idea to gender bias, the authors demonstrate that gendered concepts can steer language model outputs toward stereotypes simply by being present in the scene, whether or not the subject interacts with them. Their findings suggest that semantic leakage contributes to a form of bias that current evaluation methods may overlook.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

safety

arXiv AI

Aug 14

It's How You Ask: Gender-Associated Linguistic Bias in LLMs

arXiv:2608. 13328v1 Announce Type: cross Abstract: Professional communication is increasingly mediated by LLMs - but do these models serve all users equally?

By Katherine Van Koevering, Anjalie Field

llms safety

arXiv Computation and Language

1d ago

The Male Abstraction Bias in Internet Culture and Large Language Models

arXiv:2611.05730v1 Announce Type: cross Abstract: Two foundational aspects of human cognition, abstractness and gender, are typically examined as separable. Here, we find they are systematically link...

By Douglas Guilbeault, Bhargav Srinivasa Desikan

llms agents safety

arXiv AI

Sep 1

Man Made Language Models? Evaluating LLMs' Perpetuation of Masculine Generics Bias

arXiv:2502.10577v2 Announce Type: replace-cross Abstract: Instruct-based large language models (LLMs) have been shown to propagate and even amplify gender bias when prompted with contextually constra...

By Enzo Doyen, Amalia Todirascu

llms safety

arXiv AI

Oct 1

Gender bias across LLMs is common and highly heterogeneous

arXiv:2609.38036v2 Announce Type: replace-cross Abstract: Understanding gender biases in large language models (LLMs) is increasingly important as these systems become embedded in decision-support to...

By Edoardo Bolzoni, Valerio Capraro

llms safety

arXiv AI

Jun 2

Failure of contextual invariance in large language models

arXiv:2603. 23485v2 Announce Type: replace-cross Abstract: Standard evaluation practices assume that large language model (LLM) outputs are stable when prompts are embedded in contextually equivalent discourses.

By Sagar Kumar, Ariel Flint, Luca Maria Aiello, Andrea Baronchelli

llms benchmarks safety

arXiv AI

Sep 30

Gender bias across LLMs is common and highly heterogenous

arXiv:2609.38036v1 Announce Type: cross Abstract: Understanding gender biases in large language models (LLMs) is increasingly important as these systems become embedded in decision-support tools with...

By Edoardo Bolzoni, Valerio Capraro

llms safety

One email a morning, machine-written

Related stories

It's How You Ask: Gender-Associated Linguistic Bias in LLMs

The Male Abstraction Bias in Internet Culture and Large Language Models

Man Made Language Models? Evaluating LLMs' Perpetuation of Masculine Generics Bias

Gender bias across LLMs is common and highly heterogeneous

Failure of contextual invariance in large language models

Gender bias across LLMs is common and highly heterogenous