arXiv：cs.CL· Bo Shao, Yihan Ma, Yiting Qu, Michael Backes, Yang Zhang·· 16 小时前
MemeTrace：基于多模态 LLM 智能体的表情包溯源与安全分析
MemeTrace: A Multimodal LLM-Based Agent for Safety-Aware Meme Provenance Analysis
AI 导读
MemeTrace 是一个基于多模态 LLM 的智能体，可自动追踪新兴表情包的来源与潜在风险。研究在包含 100 个真实表情包的数据集 Meme100 上评估，结果显示其性能大幅优于 VLM 基线，在检测虚假信息与敏感内容等不安全表情包上准确率更高，且在视觉扰动下保持稳健。该工作已被 EMNLP 2026 Findings 接收。
正文
Abstract: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.
| Comments: | Accepted to Findings of EMNLP 2026 |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY) |
| Cite as: | arXiv:2610.19267 [cs.AI] |
| (or arXiv:2610.19267v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19267 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bo Shao [view email]
[v1]
Tue, 13 Oct 2026 22:38:06 UTC (8,678 KB)
来源：arXiv：cs.CL · arxiv.org