arXiv Computation and Language September 11, 2026 By Nour Bouchouchi, Thibault Laugel, Xavier Renard, Christophe Marsala, Marie-Jeanne Lesot, Marcin Detyniecki

Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and Study

Read the original on arXiv Computation and Language →

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.

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.

arXiv Computer Vision

2d ago

ViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language Models

The paper introduces ViD, a vision‑dominant gender bias mitigation framework for large vision‑language models. ViD uses causal analysis of attention patterns and dual mechanisms—backdoor adjustment and refined token selection—to suppress bias while preserving reasoning and generation quality. Experiments show a 14.7% reduction in gender bias on FACET and significant improvements on MS COCO image captioning, all without extra training overhead.

By Zhipeng Zhao, Zhaoqiang Wei, Peishun Liu, Youwei Zhao, Ruichun Tang

llms multimodal benchmarks 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 Machine Learning

Jul 23

Evaluating and Mitigating Gender Bias in Pre-trained Embeddings for ML-based Recruitment

arXiv:2607. 20073v1 Announce Type: new Abstract: AI-based recruitment systems that rely on machine learning models trained on historical CV data, risk perpetuating and amplifying social biases.

By Farnaz Faramarzi Lighvan, Lynn Houthuys

llms rag safety

arXiv AI

Jul 8

RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs

arXiv:2607. 05679v1 Announce Type: cross Abstract: Language models (LMs) exhibit problematic biases, such as stereotypes.

By Damian Hodel, Jevin West, Aylin Caliskan

llms rag benchmarks

arXiv AI

Aug 18

DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Decoupled Reasoning

arXiv:2502. 11603v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit strong natural language understanding capabilities but also inherit and amplify societal biases, particularly gender bias, raising fairness concerns.

By Hongye Qiu, Yue Xu, Yi Wang, Meikang Qiu, Wenjie Wang

llms multimodal 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

One email a morning, machine-written

Related stories

ViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language Models

Failure of contextual invariance in large language models

Evaluating and Mitigating Gender Bias in Pre-trained Embeddings for ML-based Recruitment

RPAM: A Principled Metric for Evaluating Associations in Language Models with High Predictive Validity in Downstream Outputs

DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Decoupled Reasoning

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