# Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection

arXiv: https://arxiv.org/abs/2508.10644 · HTML: https://mlsanity.com/paper/2508.10644/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 60 references that are in the map.
- First posted on arXiv 14 Aug 2025.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)](https://mlsanity.com/paper/1906.01815/) (2019)
- [Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations](https://mlsanity.com/paper/2210.17444/) (2022)
- [A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis](https://mlsanity.com/paper/2006.15955/) (2020)
- [SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks](https://mlsanity.com/paper/2303.00733/) (2023)
- [A Multimodal Corpus for Emotion Recognition in Sarcasm](https://mlsanity.com/paper/2206.02119/) (2022)
- [A Report on the 2020 Sarcasm Detection Shared Task](https://mlsanity.com/paper/2005.05814/) (2020)
- [Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning](https://mlsanity.com/paper/2404.09403/) (2024)
- [Increasing Visual Awareness in Multimodal Neural Machine Translation from an Information Theoretic Perspective](https://mlsanity.com/paper/2210.08478/) (2022)
- [A Quantum Probability Driven Framework for Joint Multi-Modal Sarcasm, Sentiment and Emotion Analysis](https://mlsanity.com/paper/2306.03650/) (2023)
- [Neural Estimators for Conditional Mutual Information Using Nearest Neighbors Sampling](https://mlsanity.com/paper/2006.07225/) (2020)
- [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 is a complex task that requires distinguishing subtle complementary signals across modalities while filtering out irrelevant information. Many advanced methods rely on learning shortcuts from datasets rather than extracting intended sarcasm-related features. However, our experiments show that shortcut learning impairs the model's generalization in real-world scenarios. Furthermore, we reveal the weaknesses of current modality fusion strategies for multimodal sarcasm detection through systematic experiments, highlighting the necessity of focusing on effective modality fusion for complex emotion recognition. To address these challenges, we construct MUStARD++R by removing shortcut signals from MUStARD++. Then, a Multimodal Conditional Information Bottleneck (MCIB) model is introduced to enable efficient multimodal fusion for sarcasm detection. Experimental results show that the MCIB achieves the best performance without relying on shortcut learning.