Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models

Hongzhan Lin, Ziyang Luo, Jing Ma*, Long Chen

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

3 Citations (Scopus)

Abstract

The age of social media is rife with memes. Understanding and detecting harmful memes pose a significant challenge due to their implicit meaning that is not explicitly conveyed through the surface text and image. However, existing harmful meme detection approaches only recognize superficial harm-indicative signals in an end-to-end classification manner but ignore in-depth cognition of the meme text and image. In this paper, we attempt to detect harmful memes based on advanced reasoning over the interplay of multimodal information in memes. Inspired by the success of Large Language Models (LLMs) on complex reasoning, we first conduct abductive reasoning with LLMs. Then we propose a novel generative framework to learn reasonable thoughts from LLMs for better multimodal fusion and lightweight fine-tuning, which consists of two training stages: 1) Distill multimodal reasoning knowledge from LLMs; and 2) Fine-tune the generative framework to infer harmfulness. Extensive experiments conducted on three meme datasets demonstrate that our proposed approach achieves superior performance than state-of-the-art methods on the harmful meme detection task.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics
Subtitle of host publicationEMNLP 2023
PublisherAssociation for Computational Linguistics (ACL)
Pages9114-9128
Number of pages15
ISBN (Electronic)9798891760615
DOIs
Publication statusPublished - Dec 2023
Event2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023 - Resorts World Convention Centre , Singapore, Singapore
Duration: 6 Dec 202310 Dec 2023
https://2023.emnlp.org/ (Conference website)

Conference

Conference2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023
Country/TerritorySingapore
CitySingapore
Period6/12/2310/12/23
Internet address

Scopus Subject Areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems
  • Language and Linguistics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models'. Together they form a unique fingerprint.

Cite this