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.

Similar Papers

MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detection (2025.acl-long)

Copied to clipboard

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.
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.
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.
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.
A Multimodal Framework to Detect Target Aware Aggression in Memes (2024.eacl-long)

Copied to clipboard

Challenge: Recent research on memes’ detrimental facets is skewed towards high-resource languages, such as Bengali.
Approach: They propose a dataset MIMOSA that annotates annotated memes across five aggression target categories in Bengali and propose 'Multimodal Attentive Fusion' to detect aggression targets.
Outcome: The proposed method outperforms state-of-the-art methods in Bengali and in low-resource languages.
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.
Characterizing the Entities in Harmful Memes: Who is the Hero, the Villain, the Victim? (2023.eacl-main)

Copied to clipboard

Challenge: A common problem associated with meme comprehension lies in detecting the entities referenced and characterizing the role of each of these entities.
Approach: They propose to use a memes dataset on US Politics and Covid-19 memes to characterize the role of harmful entities in memes.
Outcome: The proposed model improves 4% over baseline and 1% over competing models.
MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention (2024.acl-long)

Copied to clipboard

Challenge: Existing studies on content moderation of toxic memes focus on text-based content . current research neglects the widespread influence of multimodal content like memes .
Approach: They propose a framework leveraging Large Language Models and Visual Language Model (VLMs) for meme intervention.
Outcome: The proposed framework enables users to generate relevant and effective responses to toxic memes.
MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing evaluation approaches focus on mLLMs’ detection accuracy for binary classification tasks, which often fail to reflect the in-depth interpretive nuance of harmfulness across diverse contexts.
Approach: They propose an agent-based arena-style evaluation framework that provides context-aware and unbiased assessment for mLLMs’ understanding of multimodal harmfulness.
Outcome: The proposed framework reduces evaluation biases of judge agents and provides unbiased comparisons of mLLMs’ abilities to interpret multimodal harmfulness.

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