# Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models

arXiv: https://arxiv.org/abs/2401.13298 · HTML: https://mlsanity.com/paper/2401.13298/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 65 references that are in the map.
- First posted on arXiv 24 Jan 2024.

## Builds on (most cited first, 30 of 46)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [Complexity-Based Prompting for Multi-Step Reasoning](https://mlsanity.com/paper/2210.00720/) (2022)
- [Unsupervised Evaluation of Interactive Dialog with DialoGPT](https://mlsanity.com/paper/2006.12719/) (2020)
- [Supervised Multimodal Bitransformers for Classifying Images and Text](https://mlsanity.com/paper/1909.02950/) (2019)
- [Answering Questions by Meta-Reasoning over Multiple Chains of Thought](https://mlsanity.com/paper/2304.13007/) (2023)
- [Detecting Harmful Memes and Their Targets](https://mlsanity.com/paper/2110.00413/) (2021)
- [Prompting for Multimodal Hateful Meme Classification](https://mlsanity.com/paper/2302.04156/) (2023)
- [Detecting and Understanding Harmful Memes: A Survey](https://mlsanity.com/paper/2205.04274/) (2022)

## Built on by (most cited first, 18 of 18)

- [Content Moderation by LLM: From Accuracy to Legitimacy](https://mlsanity.com/paper/2409.03219/) (2024)
- [Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities](https://mlsanity.com/paper/2406.07353/) (2024)
- [ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection](https://mlsanity.com/paper/2510.08630/) (2025)
- [Read as You See: Guiding Unimodal LLMs for Low-Resource Explainable Harmful Meme Detection](https://mlsanity.com/paper/2506.08477/) (2025)
- [MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detection](https://mlsanity.com/paper/2410.20140/) (2024)
- [From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought Alignment](https://mlsanity.com/paper/2506.18919/) (2025)
- [MGHFT: Multi-Granularity Hierarchical Fusion Transformer for Cross-Modal Sticker Emotion Recognition](https://mlsanity.com/paper/2507.18929/) (2025)
- [Improving Multimodal Hateful Meme Detection Exploiting LMM-Generated Knowledge](https://mlsanity.com/paper/2504.09914/) (2025)
- [Detecting and Mitigating Hateful Content in Multimodal Memes with Vision-Language Models](https://mlsanity.com/paper/2505.00150/) (2025)
- [CRAVE: A Conflicting Reasoning Approach for Explainable Claim Verification Using LLMs](https://mlsanity.com/paper/2504.14905/) (2025)
- [VModA: An Effective Framework for Adaptive NSFW Image Moderation](https://mlsanity.com/paper/2505.23386/) (2025)
- [From Shallow Humor to Metaphor: Towards Label-Free Harmful Meme Detection via LMM Agent Self-Improvement](https://mlsanity.com/paper/2512.21598/) (2025)
- [EVL-MCoT: Enhanced Vision-Language Multi-CoT for Harmful Meme Detection](https://mlsanity.com/paper/2607.22016/) (2026)
- [Unpacking Hateful Memes: Presupposed Context and False Claims](https://mlsanity.com/paper/2510.09935/) (2025)
- [VERHallu: Evaluating and Mitigating Event Relation Hallucination in Video Large Language Models](https://mlsanity.com/paper/2601.10010/) (2026)
- [When Youth Enter the Algorithmic Wild: Discovering and Understanding Potentially Harmful Teen Videos on Douyin and Kwai](https://mlsanity.com/paper/2605.23598/) (2026)
- [Decoding Multimodal Cues: Unveiling the Implicit Meaning Behind Hateful Videos](https://mlsanity.com/paper/2606.11953/) (2026)
- [Learn Before You Judge: Progressive Knowledge-to-Decision Alignment for Explainable Hateful Meme Detection](https://mlsanity.com/paper/2609.19778/) (2026)

## Abstract (arXiv)

The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not explicitly conveyed through the surface text and image. However, existing harmful meme detection methods do not present readable explanations that unveil such implicit meaning to support their detection decisions. In this paper, we propose an explainable approach to detect harmful memes, achieved through reasoning over conflicting rationales from both harmless and harmful positions. Specifically, inspired by the powerful capacity of Large Language Models (LLMs) on text generation and reasoning, we first elicit multimodal debate between LLMs to generate the explanations derived from the contradictory arguments. Then we propose to fine-tune a small language model as the debate judge for harmfulness inference, to facilitate multimodal fusion between the harmfulness rationales and the intrinsic multimodal information within memes. In this way, our model is empowered to perform dialectical reasoning over intricate and implicit harm-indicative patterns, utilizing multimodal explanations originating from both harmless and harmful arguments. Extensive experiments on three public meme datasets demonstrate that our harmful meme detection approach achieves much better performance than state-of-the-art methods and exhibits a superior capacity for explaining the meme harmfulness of the model predictions.