REVIEW 6 cited by
Fairness and Bias in Multimodal AI: A Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The importance of addressing fairness and bias in artificial intelligence (AI) systems cannot be over-emphasized. Mainstream media has been awashed with news of incidents around stereotypes and other types of bias in many of these systems in recent years. In this survey, we fill a gap with regards to the relatively minimal study of fairness and bias in Large Multimodal Models (LMMs) compared to Large Language Models (LLMs), providing 50 examples of datasets and models related to both types of AI along with the challenges of bias affecting them. We discuss the less-mentioned category of mitigating bias, preprocessing (with particular attention on the first part of it, which we call preuse). The method is less-mentioned compared to the two well-known ones in the literature: intrinsic and extrinsic mitigation methods. We critically discuss the various ways researchers are addressing these challenges. Our method involved two slightly different search queries on two reputable search engines, Google Scholar and Web of Science (WoS), which revealed that for the queries 'Fairness and bias in Large Multimodal Models' and 'Fairness and bias in Large Language Models', 33,400 and 538,000 links are the initial results, respectively, for Scholar while 4 and 50 links are the initial results, respectively, for WoS. For reproducibility and verification, we provide links to the search results and the citations to all the final reviewed papers. We believe this work contributes to filling this gap and providing insight to researchers and other stakeholders on ways to address the challenges of fairness and bias in multimodal and language AI.
Forward citations
Cited by 6 Pith papers
-
Symphony of Bias: Exploring Gender Associations with Musical Instruments in Multimodal LLMs
Multimodal LLMs reproduce gendered instrument stereotypes across text, image, and audio inputs, with text showing the strongest and audio the weakest alignment.
-
FAIRTOPIA: Envisioning Multi-Agent Guardianship for Disrupting Unfair AI Pipelines
FAIRTOPIA proposes a three-layer, multi-agent architecture for continuous AI fairness guardianship, but offers only a conceptual design and no validation.
-
A Stereotype Content Analysis on Color-related Social Bias in Large Vision Language Models
Eight vision-language models show consistent color-linked stereotypes in competence and warmth, measured with a new SCM-based projection metric on a color-controlled image benchmark.
-
Automated Evaluation of Gender Bias Across 13 Large Multimodal Models
A benchmark of 13 image-generation models finds that most amplify occupational gender stereotypes, producing men in 93% of male-stereotyped prompts and 22.5% of female-stereotyped prompts, while one model approached parity.
-
Inference Time Debiasing Concepts in Diffusion Models
DeCoDi subtracts a biased-concept guidance term during diffusion inference to shift generated images away from targeted stereotypes, with evaluation on gender, ethnicity, and age.
-
Findings of MEGA: Maths Explanation with LLMs using the Socratic Method for Active Learning
University students preferred an interactive Socratic, multiple-choice LLM math tutor over step-by-step explanations for difficult problems, but not for easy ones, and the effect was only statistically significant for...
Discussion (0). Continue with ORCID to comment.