# ViSP: A PPO-Driven Framework for Sarcasm Generation with Contrastive Learning

arXiv: https://arxiv.org/abs/2507.09482 · HTML: https://mlsanity.com/paper/2507.09482/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 33 references that are in the map.
- First posted on arXiv 13 Jul 2025.

## Builds on (most cited first, 14 of 14)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)](https://mlsanity.com/paper/1906.01815/) (2019)
- [MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System](https://mlsanity.com/paper/2307.07135/) (2023)
- [Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation](https://mlsanity.com/paper/2306.16650/) (2023)
- [Debiasing Multimodal Sarcasm Detection with Contrastive Learning](https://mlsanity.com/paper/2312.10493/) (2023)
- [Explaining (Sarcastic) Utterances to Enhance Affect Understanding in Multimodal Dialogues](https://mlsanity.com/paper/2211.11049/) (2022)
- [Indonesian Social Media Sentiment Analysis With Sarcasm Detection](https://mlsanity.com/paper/1505.03085/) (2015)

## Abstract (arXiv)

Human emotions are complex, with sarcasm being a subtle and distinctive form. Despite progress in sarcasm research, sarcasm generation remains underexplored, primarily due to the overreliance on textual modalities and the neglect of visual cues, as well as the mismatch between image content and sarcastic intent in existing datasets. In this paper, we introduce M2SaG, a multimodal sarcasm generation dataset with 4,970 samples, each containing an image, a sarcastic text, and a sarcasm target. To benchmark M2SaG, we propose ViSP, a generation framework that integrates Proximal Policy Optimization (PPO) and contrastive learning. PPO utilizes reward scores from DIP to steer the generation of sarcastic texts, while contrastive learning encourages the model to favor outputs with higher reward scores. These strategies improve overall generation quality and produce texts with more pronounced sarcastic intent. We evaluate ViSP across five metric sets and find it surpasses all baselines, including large language models, underscoring their limitations in sarcasm generation. Furthermore, we analyze the distributions of Sarcasm Scores and Factual Incongruity for both M2SaG and the texts generated by ViSP. The generated texts exhibit higher mean Sarcasm Scores (0.898 vs. 0.770) and Factual Incongruity (0.768 vs. 0.739), demonstrating that ViSP produces higher-quality sarcastic content than the original dataset. % The dataset and code will be publicly available. Our dataset and code will be released at textithttps://github.com/wclapply/ViSP.