Challenge: a rapid expansion of memes on social media highlights the need for effective methods to detect harmful content.
Approach: They propose a multi-agent framework for zero-shot harmful meme detection that does not rely on annotated data.
Outcome: The proposed framework outperforms existing zero-shot approaches on three meme datasets.

Similar Papers

Towards Low-Resource Harmful Meme Detection with LMM Agents (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for harmful meme detection are limited due to the dynamic nature of memes . eliciting knowledge-revising behavior within the LMM agent is a key factor in achieving this goal .
Approach: They propose an agency-driven framework for low-resource harmful meme detection . they use annotated memes to leverage label information as auxiliary signals for model .
Outcome: The proposed framework achieves superior performance than state-of-the-art methods on the low-resource harmful meme detection task.
MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets (2021.findings-emnlp)

Copied to clipboard

Challenge: a growing number of harmful memes are being used for trolling, cyberbullying and abuse . a new approach to detect harmful meme images and texts is emerging .
Approach: They propose a multimodal deep neural network that detects harmful memes . they extend the recently released HarMeme dataset with additional memes and a new topic .
Outcome: The proposed framework outperforms rival methods in detecting harmful memes and their target social entities.
Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for harmful meme detection ignore in-depth cognition of meme text and image . authors propose a framework for learning reasonable thoughts from LLMs for better multimodal fusion .
Approach: They propose to use large language models to learn reasonable thoughts from LLMs for better multimodal fusion and lightweight fine-tuning.
Outcome: The proposed approach achieves superior performance than state-of-the-art methods on the harmful meme detection task.
DISARM: Detecting the Victims Targeted by Harmful Memes (2022.findings-naacl)

Copied to clipboard

Challenge: DISARM is a framework that uses named-entity recognition and person identification to detect all entities a meme is referring to and then incorporates a novel contextualized deep neural network to classify whether the meme intends to harm these entities.
Approach: They propose a framework that uses named-entity recognition and person identification to detect all entities a meme is referring to and incorporates a novel contextualized deep neural network to classify whether the meme intends to harm them.
Outcome: The proposed framework outperforms 10 unimodal and multimodal systems and reduces error rate of harmful target identification by 9 % absolute over baseline systems.
Detecting Harmful Memes and Their Targets (2021.findings-acl)

Copied to clipboard

Challenge: a growing body of research on meme analysis has focused on detecting harmful memes and their social entities . a meme is a form of content that is often harmless and designed to look funny . but its multimodal nature and camouflaged semantics make its analysis challenging .
Approach: They propose to use multimodal models to detect harmful memes and identify social entities that harmful meme targets.
Outcome: The proposed model can detect harmful memes and the social entities they target . the proposed model lacks the appropriate contexts and is poorly validated .
AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness (2025.acl-long)

Copied to clipboard

Challenge: Existing models that assess mLLMs on harmful meme understanding are inaccurate and lack accuracy.
Approach: They propose a framework that adaptively probes the reasoning capabilities of mLLMs . their framework systematically reveals the varying performance of different target mllms a .
Outcome: The proposed framework systematically reveals the performance of different target mLLMs.
Beyond Single-View Detection: A Dual-Space Reasoning Framework for Interpretable Harmful Meme Understanding (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for identifying harmful memes rely on modal alignment or black-box classifiers . BPDMoE-Hate provides visual explanations for viewpoint selection and hierarchical structuring .
Approach: They propose a framework that conceptualizes harmful meme detection as a process of "viewpoint decoupling and hierarchical fusion" they propose BPDMoE-Hate, which generates adversarial binary perspectives via VLMs and incorporates an adaptive viewpoint gating to facilitate viewpoint selection.
Outcome: The proposed framework surpasses existing methods in performance and provides visual explanations for viewpoint selection and hierarchical structuring.
MemeDetoxNet: Balancing Toxicity Reduction and Context Preservation (2025.findings-acl)

Copied to clipboard

Challenge: Toxic memes spread harmful and offensive content and pose a significant challenge in online environments.
Approach: They propose a framework to mitigate toxicity in toxic memes by leveraging a set of pre-trained models that can interpret the visual and textual components of memes.
Outcome: The proposed framework reduces toxicity on publicly available meme datasets by 10-20% compared to the previous methods.
A Context-Aware Contrastive Learning Framework for Hateful Meme Detection and Segmentation (2025.findings-naacl)

Copied to clipboard

Challenge: Empirical experiments show HateSieve surpasses existing LMMs in performance with fewer trainable parameters .
Approach: They propose a framework to enhance detection and segmentation of hateful elements in memes by creating a triplet dataset and an Image-Text Alignment module.
Outcome: HateSieve features a new framework that creates semantically correlated memes and generates contextual embeddings for accurate meme segmentation.
MEMEX: Detecting Explanatory Evidence for Memes via Knowledge-Enriched Contextualization (2023.acl-long)

Copied to clipboard

Challenge: Besides digital archiving of memes and their metadata, there is no efficient way to deduce a meme’s context dynamically.
Approach: They propose a task to mine the context that succinctly explains the background of a meme and a related document to capture cross-modal semantic dependencies between the meme and the context.
Outcome: The proposed dataset outperforms existing systems and shows that it can capture cross-modal semantic dependencies between the meme and the context.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations