Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models

Ming Shan Hee, Shivam Sharma, Rui Cao, Palash Nandi, Preslav Nakov, Tanmoy Chakraborty, Roy Ka-Wei Lee

TL;DR

This comprehensive survey delves into the recent strides in HS moderation, spotlighting the burgeoning role of large language models (LLMs) and large multimodal models (LMMs) and the development of more nuanced, context-aware systems.

Abstract

In the evolving landscape of online communication, moderating hate speech (HS) presents an intricate challenge, compounded by the multimodal nature of digital content. This comprehensive survey delves into the recent strides in HS moderation, spotlighting the burgeoning role of large language models (LLMs) and large multimodal models (LMMs). Our exploration begins with a thorough analysis of current literature, revealing the nuanced interplay between textual, visual, and auditory elements in propagating HS. We uncover a notable trend towards integrating these modalities, primarily due to the complexity and subtlety with which HS is disseminated. A significant emphasis is placed on the advances facilitated by LLMs and LMMs, which have begun to redefine the boundaries of detection and moderation capabilities. We identify existing gaps in research, particularly in the context of underrepresented languages and cultures, and the need for solutions to handle low-resource settings. The survey concludes with a forward-looking perspective, outlining potential avenues for future research, including the exploration of novel AI methodologies, the ethical governance of AI in moderation, and the development of more nuanced, context-aware systems. This comprehensive overview aims to catalyze further research and foster a collaborative effort towards more sophisticated, responsible, and human-centric approaches to HS moderation in the digital era. WARNING: This paper contains offensive examples.

Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models

TL;DR

This comprehensive survey delves into the recent strides in HS moderation, spotlighting the burgeoning role of large language models (LLMs) and large multimodal models (LMMs) and the development of more nuanced, context-aware systems.

Abstract

In the evolving landscape of online communication, moderating hate speech (HS) presents an intricate challenge, compounded by the multimodal nature of digital content. This comprehensive survey delves into the recent strides in HS moderation, spotlighting the burgeoning role of large language models (LLMs) and large multimodal models (LMMs). Our exploration begins with a thorough analysis of current literature, revealing the nuanced interplay between textual, visual, and auditory elements in propagating HS. We uncover a notable trend towards integrating these modalities, primarily due to the complexity and subtlety with which HS is disseminated. A significant emphasis is placed on the advances facilitated by LLMs and LMMs, which have begun to redefine the boundaries of detection and moderation capabilities. We identify existing gaps in research, particularly in the context of underrepresented languages and cultures, and the need for solutions to handle low-resource settings. The survey concludes with a forward-looking perspective, outlining potential avenues for future research, including the exploration of novel AI methodologies, the ethical governance of AI in moderation, and the development of more nuanced, context-aware systems. This comprehensive overview aims to catalyze further research and foster a collaborative effort towards more sophisticated, responsible, and human-centric approaches to HS moderation in the digital era. WARNING: This paper contains offensive examples.
Paper Structure (27 sections, 2 figures, 1 table)

This paper contains 27 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Hate Speech
  3. Text-based Hate Speech
  4. Image-based Hate Speech
  5. Video-based Hate Speech
  6. Audio-based Hate Speech
  7. Methodology
  8. Large Models
  9. Hate Speech Detection
  10. Hate Speech Explanation
  11. Hate Speech Debiasing
  12. Counter Speech
  13. Challenges
  14. Data Complexity, Quality, and Sourcing.
  15. Model Performance and Generalizability.
  16. ...and 12 more sections

Figures (2)

  • Figure 1: Examples of an anti-migrant HS in different forms, encompassing text, image and/or audio modalities. The text-based, vision-language and video-based HS are taken from the Social Bias Inference Corpus (SBIC) dataset, the Facebook Hateful Memes (FHM) dataset and the Bitchute website, respectively.
  • Figure 2: Typology of HS based on modalities and tasks. The dark blue boxes are mature areas with multiple studies; light grey boxes are ongoing research, and hatched boxes are unexplored topics.