ACL Findings2025
MemeDetoxNet: Balancing Toxicity Reduction and Context Preservation
Abstract
Toxic memes often spread harmful and offensive content and pose a significant challenge in online environments. In this paper, we present MemeDetoxNet, a robust framework designed to mitigate toxicity in memes by leveraging fine-tuned pre-trained models. Our approach utilizes the interpretability of CLIP (Contrastive Language-Image Pre-Training) to identify toxic elements within the visual and textual components of memes. Our objective is to automatically assess the immorality of toxic memes and transform them into morally acceptable alternatives by employing large language models (LLMs) to replace offensive text and blurring toxic regions in the image. As a result, we proposed MemeDetoxNet that has three main primitives: (1) detection of toxic memes, (2) localizing and highlighting toxic visual and textual attributes, and (3) manipulating the toxic content to create a morally acceptable alternative. Empirical evaluation on several publicly available meme datasets shows a reduction in toxicity by approximately 10-20%. Both qualitative and quantitative analyses further demonstrate MemeDetoxNet's superior performance in detoxifying memes compared to the other methods. These results underscore MemeDetoxNet's potential as an effective tool for content moderation on online platforms 1 .
Warning: This paper includes toxic memes that contain text or images with nudity or sexual content as part of the detoxification study.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on18
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- Aligning AI With Shared Human ValuesDan Hendrycks, Collin Burns, Steven Basart, Andrew Critch et al.ICLR 2021 · 878 citations
Related papers
- MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme InterventionPrince Jha, Raghav Jain, Konika Mandal, Aman Chadha et al.ACL 2024 · 5 citations
- Self-Detoxifying Language Models via Toxification ReversalChak Tou Leong, Yi Cheng, Jiashuo Wang, Jian Wang et al.EMNLP 2023 · 12 citations
- Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language ModelsTassilo Klein, Moin NabiACL 2025
- Read as You See: Guiding Unimodal LLMs for Low-Resource Explainable Harmful Meme DetectionFengjun Pan, Xiaobao Wu, Tho Quan, Anh Tuan LuuWWW 2026 · 2 citations
- Chinese Toxic Language Mitigation via Sentiment Polarity Consistent RewritesXintong Wang, Yixiao Liu, Jingheng Pan, Liang Ding et al.EMNLP 2025 · 1 citation
