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?
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.
Related stories
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...
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 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...
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
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...
arXiv AI
Sep 1
Vision-Language Models Suppress Female Representations Under Ambiguous Input
arXiv:2605.31556v2 Announce Type: replace-cross Abstract: Alignment teaches vision-language models (VLMs) to avoid expressing demographic biases, and when gender is clearly visible they largely succe...
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.
Hugging Face Trending Papers
Aug 13
It's How You Ask: Gender-Associated Linguistic Bias in LLMs
Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more commonly used by women (hedges, tag questions, collective reference), they systematically elicit shorter, less sophisticated, and less formal responses across three document types and four models.
arXiv Computation and Language
Oct 19
Analyzing Occupational Gender Bias across the LLM Training Lifecycle
arXiv:2610.23587v1 Announce Type: new Abstract: Post-training is widely assumed to reduce the social biases language models inherit from pretraining, yet direct evidence for this assumption remains m...
arXiv Computation and Language
Sep 1
Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Bias
The paper examines how large language models (LLMs) respond to different demographic cues—such as names—when users seek advice, focusing on race and gender in a U.S. context. It finds that using different cues for the same group leads to only partially overlapping changes in model responses, producing inconsistent conclusions about personalization and unstable bias metrics. The authors argue that LLMs react to linguistic signals tied to cues rather than to stable demographic categories, and they call for evaluations that use multiple cues and consider underlying mechanisms.
arXiv AI
Sep 11
Voice or Stereotype? Disentangling Acoustic and Content-Based Gender in Speech-to-Speech Models
The study investigates how speech‑to‑speech (S2S) models handle gender, distinguishing between the acoustic voice and the content’s gender cues. Experiments across five models in English, Spanish, and Mandarin show that while the rendered voice remains unbiased, the models consistently attribute speaker gender based on textual content rather than voice. When content and voice disagree, misgendering rates soar to 90%, whereas agreement yields only 2% misgendering.