Article

Multimodal large language models encode implicit gender bias

2026-08-11

Abstract excerpt

<p>Value-aligned multimodal large language models (MLLMs) appear explicitly unbiased, yet they still encode implicit biases. Quantifying implicit biases is essential for pursuing fairness in MLLMs. However, measuring them remains an open challenge. Here, we propose reverse correlation, a widely used data-driven technique in psychology for capturing mental representations and stereotypes, as a method for uncovering...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: e76740ca-8308-5fed-96d9-5244a795198b
DOI: 10.31234/osf.io/gbnfq_v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Multimodal large language models encode implicit gender biasDOI 10.31234/osf.io/gbnfq_v1Read

Modelling Implicit Bias in Gender–Career Associations: A systematic comparison of language modelsSemantic proximity Read

Aligned but Biased: Comparing Human and Large Language Model Intergroup BiasSemantic proximity Read

Modelling Implicit Bias in Gender–Career Associations: A systematic comparison of language modelsSemantic proximity Read

Modelling Implicit Bias in Gender–Career Associations: A systematic comparison of language modelsSemantic proximity Read

Which Humans?Semantic proximity Read

Stereotypical Bias Amplification, and Reversal, in an Experimental Model of Human Interaction with Generative AISemantic proximity Read

Stereotypical Bias Amplification, and Reversal, in an Experimental Model of Human Interaction with Generative AISemantic proximity Read

Large Language Models Know How the Personality of Public Figures is Perceived by the General PublicSemantic proximity Read

Large language models capture universal relationship knowledge but compress cultural variationSemantic proximity Read

How Well Do Large Language Models Capture Human Personality?Semantic proximity Read

Synthetic Policymaking: Using LLM-Generated Personas to Predict Public Views on Existing and Prospective Policies in non-WEIRD CountriesSemantic proximity Read

Evaluating Large Language Models in Psychological Research: A Guide for ReviewersSemantic proximity Read