Examining Multimodal Gender and Content Bias in ChatGPT-4o

• URL: http://arxiv.org/abs/2411.19140v1
• Date: Thu, 28 Nov 2024 13:41:44 GMT
• Title: Examining Multimodal Gender and Content Bias in ChatGPT-4o
• Authors: Roberto Balestri,
• Abstract summary: ChatGPT-4o consistently censors sexual content and nudity, while showing leniency towards violence and drug use. A pronounced gender bias emerges, with female-specific content facing stricter regulation compared to male-specific content.
• Score: 0.0
• License:
• Abstract: This study investigates ChatGPT-4o's multimodal content generation, highlighting significant disparities in its treatment of sexual content and nudity versus violent and drug-related themes. Detailed analysis reveals that ChatGPT-4o consistently censors sexual content and nudity, while showing leniency towards violence and drug use. Moreover, a pronounced gender bias emerges, with female-specific content facing stricter regulation compared to male-specific content. This disparity likely stems from media scrutiny and public backlash over past AI controversies, prompting tech companies to impose stringent guidelines on sensitive issues to protect their reputations. Our findings emphasize the urgent need for AI systems to uphold genuine ethical standards and accountability, transcending mere political correctness. This research contributes to the understanding of biases in AI-driven language and multimodal models, calling for more balanced and ethical content moderation practices.

Related papers

• Advancing Content Moderation: Evaluating Large Language Models for Detecting Sensitive Content Across Text, Images, and Videos [0.1399948157377307]
  Governments, educators, and parents are often at odds with media platforms about how to regulate, control, and limit the spread of such content. Techniques from natural language processing and computer vision have been used widely to automatically identify and filter out sensitive content. More sophisticated algorithms for understanding the context of both text and image may open rooms for improvement in content censorship.
  arXiv  Detail & Related papers  (2024-11-26T05:29:18Z)
• The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models [58.130894823145205]
  We center transgender, nonbinary, and other gender-diverse identities to investigate how alignment procedures interact with pre-existing gender-diverse bias. Our findings reveal that DPO-aligned models are particularly sensitive to supervised finetuning. We conclude with recommendations tailored to DPO and broader alignment practices.
  arXiv  Detail & Related papers  (2024-11-06T06:50:50Z)
• Watching the Watchers: A Comparative Fairness Audit of Cloud-based Content Moderation Services [1.3654846342364306]
  This study systematically evaluations four leading cloud-based content moderation services through a third-party audit. Using a black-box audit approach and four benchmark data sets, we measure performance in explicit and implicit hate speech detection. Our analysis reveals that all services had difficulties detecting implicit hate speech, which relies on more subtle and codified messages. It seems that biases towards some groups, such as Women, have been mostly rectified, while biases towards other groups, such as LGBTQ+ and PoC remain.
  arXiv  Detail & Related papers  (2024-06-20T09:52:10Z)
• Diverse, but Divisive: LLMs Can Exaggerate Gender Differences in Opinion Related to Harms of Misinformation [8.066880413153187]
  This paper examines whether a large language model (LLM) can reflect the views of various groups when assessing the harms of misinformation. We present the TopicMisinfo dataset, containing 160 fact-checked claims from diverse topics. We find that GPT 3.5-Turbo reflects empirically observed gender differences in opinion but amplifies the extent of these differences.
  arXiv  Detail & Related papers  (2024-01-29T20:50:28Z)
• Human vs. LMMs: Exploring the Discrepancy in Emoji Interpretation and Usage in Digital Communication [68.40865217231695]
  This study examines the behavior of GPT-4V in replicating human-like use of emojis. The findings reveal a discernible discrepancy between human and GPT-4V behaviors, likely due to the subjective nature of human interpretation.
  arXiv  Detail & Related papers  (2024-01-16T08:56:52Z)
• GPT-4V(ision) as A Social Media Analysis Engine [77.23394183063238]
  This paper explores GPT-4V's capabilities for social multimedia analysis. We select five representative tasks, including sentiment analysis, hate speech detection, fake news identification, demographic inference, and political ideology detection. GPT-4V demonstrates remarkable efficacy in these tasks, showcasing strengths such as joint understanding of image-text pairs, contextual and cultural awareness, and extensive commonsense knowledge.
  arXiv  Detail & Related papers  (2023-11-13T18:36:50Z)
• DEMASQ: Unmasking the ChatGPT Wordsmith [63.8746084667206]
  We propose an effective ChatGPT detector named DEMASQ, which accurately identifies ChatGPT-generated content. Our method addresses two critical factors: (i) the distinct biases in text composition observed in human- and machine-generated content and (ii) the alterations made by humans to evade previous detection methods.
  arXiv  Detail & Related papers  (2023-11-08T21:13:05Z)
• Towards Harmful Erotic Content Detection through Coreference-Driven Contextual Analysis [0.0]
  This paper introduces a hybrid neural and rule-based context-aware system to identify harmful contextual cues in erotic content. Our model, tested on Polish text, demonstrates a promising accuracy of 84% and a recall of 80%.
  arXiv  Detail & Related papers  (2023-10-22T15:19:04Z)
• NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly [61.77957329364812]
  We introduce a framework for addressing the novel task of conversation-grounded multi-lingual, multi-cultural norm discovery. NormSAGE elicits knowledge about norms through directed questions representing the norm discovery task and conversation context. It further addresses the risk of language model hallucination with a self-verification mechanism ensuring that the norms discovered are correct.
  arXiv  Detail & Related papers  (2022-10-16T18:30:05Z)
• TIB-VA at SemEval-2022 Task 5: A Multimodal Architecture for the Detection and Classification of Misogynous Memes [9.66022279280394]
  We present a multimodal architecture that combines textual and visual features in order to detect misogynous meme content. Our solution obtained the best result in the Task-B where the challenge is to classify whether a given document is misogynous.
  arXiv  Detail & Related papers  (2022-04-13T11:03:21Z)
• Gender bias in magazines oriented to men and women: a computational approach [58.720142291102135]
  We compare the content of a women-oriented magazine with that of a men-oriented one, both produced by the same editorial group over a decade. With Topic Modelling techniques we identify the main themes discussed in the magazines and quantify how much the presence of these topics differs between magazines over time. Our results show that the frequency of appearance of the topics Family, Business and Women as sex objects, present an initial bias that tends to disappear over time.
  arXiv  Detail & Related papers  (2020-11-24T14:02:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.