GDCNet: Generative Discrepancy Comparison Network for Multimodal Sarcasm Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908793453936640 |
|---|---|
| author | Zhang, Shuguang Lian, Junhong Yu, Guoxin Xu, Baoxun Ao, Xiang |
| author_facet | Zhang, Shuguang Lian, Junhong Yu, Guoxin Xu, Baoxun Ao, Xiang |
| contents | Multimodal sarcasm detection (MSD) aims to identify sarcasm within image-text pairs by modeling semantic incongruities across modalities. Existing methods often exploit cross-modal embedding misalignment to detect inconsistency but struggle when visual and textual content are loosely related or semantically indirect. While recent approaches leverage large language models (LLMs) to generate sarcastic cues, the inherent diversity and subjectivity of these generations often introduce noise. To address these limitations, we propose the Generative Discrepancy Comparison Network (GDCNet). This framework captures cross-modal conflicts by utilizing descriptive, factually grounded image captions generated by Multimodal LLMs (MLLMs) as stable semantic anchors. Specifically, GDCNet computes semantic and sentiment discrepancies between the generated objective description and the original text, alongside measuring visual-textual fidelity. These discrepancy features are then fused with visual and textual representations via a gated module to adaptively balance modality contributions. Extensive experiments on MSD benchmarks demonstrate GDCNet's superior accuracy and robustness, establishing a new state-of-the-art on the MMSD2.0 benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20618 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GDCNet: Generative Discrepancy Comparison Network for Multimodal Sarcasm Detection Zhang, Shuguang Lian, Junhong Yu, Guoxin Xu, Baoxun Ao, Xiang Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Multimodal sarcasm detection (MSD) aims to identify sarcasm within image-text pairs by modeling semantic incongruities across modalities. Existing methods often exploit cross-modal embedding misalignment to detect inconsistency but struggle when visual and textual content are loosely related or semantically indirect. While recent approaches leverage large language models (LLMs) to generate sarcastic cues, the inherent diversity and subjectivity of these generations often introduce noise. To address these limitations, we propose the Generative Discrepancy Comparison Network (GDCNet). This framework captures cross-modal conflicts by utilizing descriptive, factually grounded image captions generated by Multimodal LLMs (MLLMs) as stable semantic anchors. Specifically, GDCNet computes semantic and sentiment discrepancies between the generated objective description and the original text, alongside measuring visual-textual fidelity. These discrepancy features are then fused with visual and textual representations via a gated module to adaptively balance modality contributions. Extensive experiments on MSD benchmarks demonstrate GDCNet's superior accuracy and robustness, establishing a new state-of-the-art on the MMSD2.0 benchmark. |
| title | GDCNet: Generative Discrepancy Comparison Network for Multimodal Sarcasm Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2601.20618 |