arXiv Computation and Language
The Male Abstraction Bias in Internet Culture and Large Language Models
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
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...
arXiv Computation and Language
Oct 22
Guilt by Association: Semantic Leakage Drives Associative Gender Bias
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.
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.
arXiv AI
Jun 9
Neutrality Bites: Gender Representation in AI-Generated Animal Stories
arXiv:2606. 07969v1 Announce Type: cross Abstract: Gender bias in AI-generated stories is a well-documented problem.
arXiv Computation and Language
Sep 11
Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and Study
The paper introduces a unified framework that simultaneously measures intrinsic (encoded) and extrinsic (expressed) gender bias in large language models using identical neutral prompts. It finds a consistent link between latent gender information and output bias, but shows that alignment via supervised fine‑tuning reduces expressed bias while leaving internal gender associations largely intact and reactivatable by adversarial prompts. The study also demonstrates that debiasing gains on structured benchmarks may not transfer to realistic tasks such as story generation.
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?