mlsanityData to 14 Oct 2026

MemeTrace: A Multimodal LLM-Based Agent for Safety-Aware Meme Provenance Analysis

arXiv 2610.19267 ↗First posted 13 Oct 2026cs.AI cs.CL cs.CYcited by 0

New in Multimodal LLMs / vision-language models; no direction yet. Multimodal LLMs / vision-language models

Abstract (arXiv)

Online memes are often carriers of unsafe content such as disinformation and propaganda. Their rapid evolution in response to news events and strong dependence on contextual information make it difficult for platforms and moderators to detect and moderate them effectively. Moreover, existing moderation studies typically classify memes as safe or unsafe based on individual images, lacking the ability to perform broader provenance analysis, i.e., where a meme originates, how it spreads, what cultural symbolism it represents, whether it poses potential risks to society, etc. To bridge this gap, we introduce MemeTrace, a multimodal LLM-based agent that automatically traces the provenance and potential risks of emerging memes. We evaluate MemeTrace on Meme100, a dataset of 100 real-world memes, using both human annotation and automatic metrics. The results demonstrate that MemeTrace substantially outperforms the VLM baseline. More importantly, MemeTrace achieves higher accuracy in detecting unsafe memes, especially those involving disinformation and sensitive content, and remains robust under visual perturbations.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 35 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

14 of 35 references.

References · 14

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memescited by 490
  3. 2020SemEval-2020 Task 8: Memotion Analysis -- The Visuo-Lingual Metaphor!cited by 78
  4. 2023Prompting for Multimodal Hateful Meme Classificationcited by 69
  5. 2024GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abusecited by 52
  6. 2020Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memescited by 51
  7. 2020A Multimodal Framework for the Detection of Hateful Memescited by 49
  8. 2018On the Origins of Memes by Means of Fringe Web Communitiescited by 47
  9. 2023Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detectioncited by 47
  10. 2024Towards Low-Resource Harmful Meme Detection with LMM Agentscited by 24
  11. 2025MIND: A Multi-agent Framework for Zero-shot Harmful Meme Detectioncited by 15
  12. 2021Dissecting the Meme Magic: Understanding Indicators of Virality in Image Memescited by 10
2 more
  1. 2024Evolver: Chain-of-Evolution Prompting to Boost Large Multimodal Models for Hateful Meme Detectioncited by 9
  2. 2024More than Memes: A Multimodal Topic Modeling Approach to Conspiracy Theories on Telegramcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval
  2. 2025From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought Alignment
  3. 2025From Shallow Humor to Metaphor: Towards Label-Free Harmful Meme Detection via LMM Agent Self-Improvement
  4. 2025AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness
  5. 2025Read as You See: Guiding Unimodal LLMs for Low-Resource Explainable Harmful Meme Detection
  6. 2024MemeCraft: Contextual and Stance-Driven Multimodal Meme Generation
  7. 2025Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study
  8. 2023Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models