# CFMS: Towards Explainable and Fine-Grained Chinese Multimodal Sarcasm Detection Benchmark

arXiv: https://arxiv.org/abs/2604.16372 · HTML: https://mlsanity.com/paper/2604.16372/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Want To Reduce Labeling Cost? GPT-3 Can Help](https://mlsanity.com/paper/2108.13487/) (2021)
- [Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)](https://mlsanity.com/paper/1906.01815/) (2019)
- [Detecting Sarcasm in Multimodal Social Platforms](https://mlsanity.com/paper/1608.02289/) (2016)
- [MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System](https://mlsanity.com/paper/2307.07135/) (2023)
- [A Survey of Multimodal Sarcasm Detection](https://mlsanity.com/paper/2410.18882/) (2024)
- [Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?](https://mlsanity.com/paper/2507.10236/) (2025)

## Built on by (most cited first, 2 of 2)

- [Reading Between the Frames of Multimodal Drivelology](https://mlsanity.com/paper/2608.04939/) (2026)
- [You Really Didn't Get That? Benchmarking Social Pragmatic Inference for Indirect and Playful Chinese Online Comments](https://mlsanity.com/paper/2609.04384/) (2026)

## Abstract (arXiv)

Multimodal sarcasm detection has recently garnered significant attention. However, existing benchmarks suffer from coarse-grained annotations and limited cultural coverage, which hinder research into fine-grained semantic understanding. To address this, we construct CFMS, the first fine-grained multimodal sarcasm dataset tailored for Chinese social media. It comprises 2,796 high-quality image-text pairs and provides a triple-level annotation framework: sarcasm identification, target recognition, and explanation generation. We find that the fine-grained explanation annotations effectively guide AI in generating images with explicit sarcastic intent. Furthermore, we curate a high-consistency parallel Chinese-English metaphor subset (200 entries each), revealing significant limitations of current models in metaphoric reasoning. To overcome the constraints of traditional retrieval methods, we propose a Reinforcement Learning-augmented In-Context Learning strategy (PGDS) to dynamically optimize exemplar selection. Extensive experiments demonstrate that CFMS provides a solid foundation for building reliable multimodal sarcasm understanding systems, and the PGDS method significantly outperforms existing baselines on key tasks. Our data and code are available at https://anonymous.4open.science/r/CFMS-E8F9.