Lune

EMNLP Findings2025

Exploring Hyperbolic Hierarchical Structure for Multimodal Rumor Detection

Md Mahbubur Rahman, Shufeng Hao, Chongyang Shi, An Lao, Jinyan Liu

Abstract

The rise of multimodal content on social platforms has led to the rapid spread of complex and persuasive false narratives, combining of text and images. Traditional rumor detection models attempt to identify such content by relying on textual cues or employing shallow multimodal fusion techniques. However, these methods often assume a simplistic one-to-one alignment between modalities, overlooking the richer hierarchical relationships across modalities, failing to capture the layered structure of meaning. In this paper, we present RumorCone, a novel method that employs hyperbolic geometry in order to preserve hierarchical, non-linear relationships, rather than representing them at a flat semantic level. First, RumorCone decomposes image and text content into three levels: base, mid, and highlevel abstractions, and embeds them in hyperbolic space to model their tree-like semantic structure. Second, a dynamic hyperbolic multimodal attention mechanism aligns features across modalities and levels, and a flexible fusion strategy adjusts the contribution of each modality based on alignment quality. Our experiments indicate the importance of hierarchical semantic modeling for robust and interpretable multimodal rumor detection.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Frequency Spectrum Is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor Detector cites Hierarchical Multi-modal Contextual Attention Network for Fake News Detection
  • Hyperbolic Image-text Representations cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on14

  1. An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
  2. Multimodal Fusion with Co-Attention Networks for Fake News DetectionYang Wu, Pengwei Zhan, Yunjian Zhang, Liming Wang et al.ACL Findings 2021 · 343 citations
  3. Hierarchical Multi-modal Contextual Attention Network for Fake News DetectionShengsheng Qian, Jinguang Wang, Jun Hu, Quan Fang et al.SIGIR 2021 · 273 citations
  4. Hyperbolic Image-text RepresentationsKaran Desai, Maximilian Nickel, Tanmay Rajpurohit, Justin Johnson et al.ICML 2023 · 137 citations
  5. Frequency Spectrum Is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor DetectorAn Lao, Qi Zhang, Chongyang Shi, Longbing Cao et al.AAAI 2024 · 46 citations

Related papers

  1. Multi-Scale Spectral Selection and Entropy-Guided Uncertainty Fusion for Multimodal Rumor DetectionZongliang Han, Wenyu Guo, Guoqing Jin, Yang Liu et al.ACL Findings 2026
  2. Inconsistency Matters: A Knowledge-guided Dual-inconsistency Network for Multi-modal Rumor DetectionMengzhu Sun, Xi Zhang, Jianqiang Ma, Yazheng LiuEMNLP Findings 2021 · 19 citations
  3. Public Wisdom Matters! Discourse-Aware Hyperbolic Fourier Co-Attention for Social Text ClassificationKarish Grover, S. M. Phaneendra Angara, Md. Shad Akhtar, Tanmoy ChakrabortyNeurIPS 2022 · 19 citations
  4. Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention NetworksHongzhan Lin, Jing Ma, Mingfei Cheng, Zhiwei Yang et al.EMNLP 2021 · 53 citations
  5. Rumor Detection with Field of Linear and Non-Linear PropagationAn Lao, Chongyang Shi, Yayi YangWWW 2021 · 63 citations
Dusk over the sea between two cliffs drawn in fine vertical lines