# DocMSU: A Comprehensive Benchmark for Document-level Multimodal Sarcasm Understanding

arXiv: https://arxiv.org/abs/2312.16023 · HTML: https://mlsanity.com/paper/2312.16023/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 26 Dec 2023.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Local Relation Networks for Image Recognition](https://mlsanity.com/paper/1904.11491/) (2019)
- [UnitBox: An Advanced Object Detection Network](https://mlsanity.com/paper/1608.01471/) (2016)
- [Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)](https://mlsanity.com/paper/1906.01815/) (2019)
- [A Large Self-Annotated Corpus for Sarcasm](https://mlsanity.com/paper/1704.05579/) (2017)
- [A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2101.00816/) (2021)
- [FakeSV: A Multimodal Benchmark with Rich Social Context for Fake News Detection on Short Video Platforms](https://mlsanity.com/paper/2211.10973/) (2022)

## Built on by (most cited first, 7 of 7)

- [VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization](https://mlsanity.com/paper/2510.06040/) (2025)
- [Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly](https://mlsanity.com/paper/2412.07183/) (2024)
- [VAGUE: Visual Contexts Clarify Ambiguous Expressions](https://mlsanity.com/paper/2411.14137/) (2024)
- [InterCLIP-MEP: Interactive CLIP and Memory-Enhanced Predictor for Multi-modal Sarcasm Detection](https://mlsanity.com/paper/2406.16464/) (2024)
- [Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models](https://mlsanity.com/paper/2503.12149/) (2025)
- [Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models](https://mlsanity.com/paper/2605.08145/) (2026)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)

## Abstract (arXiv)

Multimodal Sarcasm Understanding (MSU) has a wide range of applications in the news field such as public opinion analysis and forgery detection. However, existing MSU benchmarks and approaches usually focus on sentence-level MSU. In document-level news, sarcasm clues are sparse or small and are often concealed in long text. Moreover, compared to sentence-level comments like tweets, which mainly focus on only a few trends or hot topics (e.g., sports events), content in the news is considerably diverse. Models created for sentence-level MSU may fail to capture sarcasm clues in document-level news. To fill this gap, we present a comprehensive benchmark for Document-level Multimodal Sarcasm Understanding (DocMSU). Our dataset contains 102,588 pieces of news with text-image pairs, covering 9 diverse topics such as health, business, etc. The proposed large-scale and diverse DocMSU significantly facilitates the research of document-level MSU in real-world scenarios. To take on the new challenges posed by DocMSU, we introduce a fine-grained sarcasm comprehension method to properly align the pixel-level image features with word-level textual features in documents. Experiments demonstrate the effectiveness of our method, showing that it can serve as a baseline approach to the challenging DocMSU. Our code and dataset are available at https://github.com/Dulpy/DocMSU.