arXiv Computation and Language September 18, 2026 By Bo Xu, Chenyuan Wang, Xinyu Chen, Quanhao Zhu, Rui Lin, Liang Zhao, Hongfei Lin, Feng Xia

Learn Before You Judge: Progressive Knowledge-to-Decision Alignment for Explainable Hateful Meme Detection

Read the original on arXiv Computation and Language →

The paper introduces ProKDA, a progressive knowledge-to-decision alignment framework for explainable hateful meme detection. ProKDA separates explanation generation and label prediction into three sequential training stages—background knowledge learning, hatefulness detection learning, and hatefulness boundary alignment—reducing task interference. Experiments on three public benchmarks demonstrate that ProKDA achieves state‑of‑the‑art detection performance while providing accurate, evidence‑supported explanations for moderation decisions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Aug 25

From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought Alignment

The paper introduces MemeMind, a large-scale dataset for detecting harmful memes that includes a detailed taxonomy and Chain-of-Thought reasoning annotations. It also proposes MemeGuard, a multimodal framework that uses a three-stage training strategy to improve visual understanding, reasoning, and discrimination of harmful content. Experiments show MemeGuard surpasses current state-of-the-art methods on MemeMind, advancing detection accuracy and interpretability.

By Hexiang Gu, Qifan Yu, Yuan Liu, Zikang Li, Saihui Hou, Jian Zhao, Zhaofeng He

multimodal benchmarks safety

arXiv AI

Jun 16

Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes

arXiv:2606. 15307v1 Announce Type: cross Abstract: Hateful and propagandistic memes exploit the interplay between images and text to convey harmful intent that neither modality reveals alone.

By Mohamed Bayan Kmainasi, Mucahid Kutlu, Ali Ezzat Shahroor, Abul Hasnat, Firoj Alam

llms reinforcement-learning efficiency multimodal benchmarks

arXiv AI

Jul 31

TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech

arXiv:2601. 11178v3 Announce Type: replace Abstract: Social media platforms are increasingly dominated by long-form multimodal content, where harmful narratives are constructed through a complex interplay of audio, visual, and textual cues.

By Girish A. Koushik, Helen Treharne, Diptesh Kanojia

llms reinforcement-learning multimodal benchmarks safety

arXiv AI

Jul 20

Beyond a Joke: Multi-Angle Reasoning for Detecting and Explaining Harmful Humor in Memes

arXiv:2607. 15442v1 Announce Type: new Abstract: Internet memes intertwine visual cues, textual content, and cultural context, making them particularly challenging to interpret in scenarios where humor, sarcasm, and harmful intent coexist.

By Shanhong Liu, Pai Chet Ng, De Wen Soh, Malika Meghjani, Konstantinos N. Plataniotis

llms multimodal benchmarks safety

arXiv AI

Aug 18

HarmTrace: Anchor-Calibrated Decoupled Optimization for Fine-Grained Target Identification in Harmful Memes

arXiv:2608. 16622v1 Announce Type: cross Abstract: Multimodal harmful meme detection is typically formulated as image--text harmfulness classification.

By Yujia Li, Yiqun Zhang, Zihan Cheng, Yijie Huang, Tenglong Ye, Zihan Wang, Xiaocui Yang, Shi Feng, Yifei Zhang, Daling Wang

llms fine-tuning multimodal

Hugging Face Trending Papers

Jul 29

AHA-Memes: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes

Hateful memes are a growing form of multimodal online harm, where hostile intent is often conveyed through the joint interpretation of images, text, cultural references, and implicit targets. While hateful meme detection has advanced in high-resource languages, Arabic remains underexplored, with existing meme resources focusing mainly on propaganda or coarse harmful-content labels.

llms fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought Alignment

Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes

TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech

Beyond a Joke: Multi-Angle Reasoning for Detecting and Explaining Harmful Humor in Memes

HarmTrace: Anchor-Calibrated Decoupled Optimization for Fine-Grained Target Identification in Harmful Memes

AHA-Memes: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes