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

Hongzhan Lin, Ziyang Luo, Jing Ma, Long Chen

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.
Anthology ID:
2023.findings-emnlp.611
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9114–9128
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.611
DOI:
10.18653/v1/2023.findings-emnlp.611
Bibkey:
Cite (ACL):
Hongzhan Lin, Ziyang Luo, Jing Ma, and Long Chen. 2023. Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9114–9128, Singapore. Association for Computational Linguistics.
Cite (Informal):
Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models (Lin et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-emnlp.611.pdf
PDF Search