# PC-MNet: Dual-Level Congruity Modeling for Multimodal Sarcasm Detection via Polarity-Modulated Attention

arXiv: https://arxiv.org/abs/2605.02447 · HTML: https://mlsanity.com/paper/2605.02447/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 37 references that are in the map.
- First posted on arXiv 4 May 2026.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [Reasoning with Sarcasm by Reading In-between](https://mlsanity.com/paper/1805.02856/) (2018)
- [A Multimodal Corpus for Emotion Recognition in Sarcasm](https://mlsanity.com/paper/2206.02119/) (2022)
- [Prompt-based Learning for Unpaired Image Captioning](https://mlsanity.com/paper/2205.13125/) (2022)
- [SarcasmBench: Towards Evaluating Large Language Models on Sarcasm Understanding](https://mlsanity.com/paper/2408.11319/) (2024)
- [A Survey of Multimodal Sarcasm Detection](https://mlsanity.com/paper/2410.18882/) (2024)
- [The Role of Conversation Context for Sarcasm Detection in Online Interactions](https://mlsanity.com/paper/1707.06226/) (2017)
- [Is Sarcasm Detection A Step-by-Step Reasoning Process in Large Language Models?](https://mlsanity.com/paper/2407.12725/) (2024)
- [Debiasing Multimodal Sarcasm Detection with Contrastive Learning](https://mlsanity.com/paper/2312.10493/) (2023)
- [Multi-View Incongruity Learning for Multimodal Sarcasm Detection](https://mlsanity.com/paper/2412.00756/) (2024)
- [FiLMing Multimodal Sarcasm Detection with Attention](https://mlsanity.com/paper/2110.00416/) (2021)
- [VyAnG-Net: A Novel Multi-Modal Sarcasm Recognition Model by Uncovering Visual, Acoustic and Glossary Features](https://mlsanity.com/paper/2408.10246/) (2024)

## Abstract (arXiv)

Multimodal sarcasm detection, which aims to precisely identify pragmatic incongruities between literal text and nonverbal cues, has gained substantial attention in multimodal understanding. Recent advancements have predominantly relied on na"ive similarity-based attention mechanisms and uniform late fusion strategies.Furthermore, given that functional entanglement restricts traditional late fusions, we incorporate a scalar congruity routing mechanism and a prior-guided contextual graph. This mechanism anchors a generalized incongruity manifold through a two-stage asymmetric optimization driven by inconsistency-aware contrastive learning, selectively fusing only the most discriminative multi-granularity evidence. Extensive experiments on the textttMUStARD benchmark and its spurious-correlation-mitigated balanced datasets demonstrate that our approach achieves new state-of-the-art performance, surpassing the strongest multimodal baseline by a substantial 3.14% improvement in Macro-F1. By architecturally isolating atomic, composition, and contextual conflicts. This work provides a robust, decoupled paradigm for modeling subtle pragmatic incongruities in human communication.