# Dual Modality-Aware Gated Prompt Tuning for Few-Shot Multimodal Sarcasm Detection

arXiv: https://arxiv.org/abs/2507.04468 · HTML: https://mlsanity.com/paper/2507.04468/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 54 references that are in the map.
- First posted on arXiv 6 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition](https://mlsanity.com/paper/2303.11313/) (2023)
- [E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning](https://mlsanity.com/paper/2307.13770/) (2023)
- [Prompting for Multimodal Hateful Meme Classification](https://mlsanity.com/paper/2302.04156/) (2023)
- [Improving Visual Prompt Tuning for Self-supervised Vision Transformers](https://mlsanity.com/paper/2306.05067/) (2023)
- [Detecting Sarcasm in Multimodal Social Platforms](https://mlsanity.com/paper/1608.02289/) (2016)
- [A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1610.08815/) (2016)
- [Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement](https://mlsanity.com/paper/2210.03501/) (2022)
- [Modelling Context with User Embeddings for Sarcasm Detection in Social Media](https://mlsanity.com/paper/1607.00976/) (2016)
- [The Role of Conversation Context for Sarcasm Detection in Online Interactions](https://mlsanity.com/paper/1707.06226/) (2017)
- [Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning](https://mlsanity.com/paper/2308.04828/) (2023)
- [Are Word Embedding-based Features Useful for Sarcasm Detection?](https://mlsanity.com/paper/1610.00883/) (2016)
- [A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict](https://mlsanity.com/paper/2109.03587/) (2021)
- ["Laughing at you or with you": The Role of Sarcasm in Shaping the Disagreement Space](https://mlsanity.com/paper/2101.10952/) (2021)

## Built on by (most cited first, 1 of 1)

- [Large Language Models for Subjective Language Understanding: A Survey](https://mlsanity.com/paper/2508.07959/) (2025)

## Abstract (arXiv)

The widespread use of multimodal content on social media has heightened the need for effective sarcasm detection to improve opinion mining. However, existing models rely heavily on large annotated datasets, making them less suitable for real-world scenarios where labeled data is scarce. This motivates the need to explore the problem in a few-shot setting. To this end, we introduce DMDP (Deep Modality-Disentangled Prompt Tuning), a novel framework for few-shot multimodal sarcasm detection. Unlike prior methods that use shallow, unified prompts across modalities, DMDP employs gated, modality-specific deep prompts for text and visual encoders. These prompts are injected across multiple layers to enable hierarchical feature learning and better capture diverse sarcasm types. To enhance intra-modal learning, we incorporate a prompt-sharing mechanism across layers, allowing the model to aggregate both low-level and high-level semantic cues. Additionally, a cross-modal prompt alignment module enables nuanced interactions between image and text representations, improving the model's ability to detect subtle sarcastic intent. Experiments on two public datasets demonstrate DMDP's superior performance in both few-shot and extremely low-resource settings. Further cross-dataset evaluations show that DMDP generalizes well across domains, consistently outperforming baseline methods.