Research map / Vision-language and multimodal / Multimodal LLMs
S³-MSD: Large Vision-Language Model for Explainable and Generalizable Multi-modal Sarcasm Detection
Zhihong Zhu, Fan Zhang, Yunyan Zhang, Jinghan Sun, Guimin Hu, Hao Wu, Yuyan Chen, Bowen Xing, Xian Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces S³-MSD, a large vision-language model for explainable and generalizable multimodal sarcasm detection on image-text pairs.
Problem
Multimodal sarcasm detection (MSD) on image-text pairs suffers from lack of explainability and weak generalizability across datasets.
Approach
Proposes an LVLM-based approach (S³-MSD) aimed at producing explainable sarcasm predictions while generalizing better than prior MSD methods; specific mechanism not stated in the available abstract.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add self-training (iterative bootstrapping of explanations from correct answers) (ablation) | S3-MSD (LLaVA-1.5-7B) · MMSD2.0 | accuracy (%): 86.65 -> 88.69 | Improved |
| add self-calibrating (condition on incorrect explanation to produce correct one) (ablation) | S3-MSD (LLaVA-1.5-7B) · MMSD2.0 | accuracy (%): 87.64 -> 88.69 | Improved |
| add self-focusing (image-only DPO with noised entity regions) (ablation) | S3-MSD (LLaVA-1.5-7B) · MMSD2.0 | accuracy (%): 87.31 -> 88.69 | Improved |
| add self-training (ablation) | S3-MSD (LLaVA-1.5-7B) · RedEval (OOD) | accuracy (%): 84.12 -> 85.98 | Improved |
| add self-focusing (ablation) | S3-MSD (LLaVA-1.5-7B) · RedEval (OOD) | accuracy (%): 84.64 -> 85.98 | Improved |
| add self-calibrating (ablation) | S3-MSD (LLaVA-1.5-7B) · RedEval (OOD) | accuracy (%): 85.14 -> 85.98 | Improved |
| replace self-calibrating with textual DPO (ablation) | S3-MSD · MMSD2.0 and RedEval | accuracy, P, R, F1 | Hurt |
| train with explanations via S3-MSD instead of golden labels only | LLaVA-1.5-7B · MMSD2.0 | accuracy (%): 85.18 -> 88.69 | Improved |
| use S3-MSD instead of V-STaR (k = 5) | LLaVA-1.5-7B · RedEval (OOD) | accuracy (%): 84.73 -> 85.98 | Improved |
| apply S3-MSD to Qwen2-VL-7B and Qwen2.5-VL-7B backbones | S3-MSD · MMSD2.0* subtest (500 instances) | accuracy | Improved |
| use S3-MSD instead of untuned closed-source LVLMs (GPT-4o, o3, Gemini) | MMSD2.0* subtest · MMSD2.0* subtest | accuracy | Improved |
| fine-tune S3-MSD on MORE for explanation generation | S3-MSD · MORE | BLEU-4: 34.25 vs TURBO 35.26 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BLIP2-2.7b — BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation (ICML 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Debiasing Multimodal Sarcasm Detection with Contrastive Learning (AAAI 2024 · similarity 0.90)
- G^2SAM: Graph-Based Global Semantic Awareness Method for Multimodal Sarcasm Detection (AAAI 2024 · similarity 0.89)
- DocMSU: A Comprehensive Benchmark for Document-Level Multimodal Sarcasm Understanding (AAAI 2024 · similarity 0.89)
- Well, Now We Know! Unveiling Sarcasm: Initiating and Exploring Multimodal Conversations with Reasoning (AAAI 2024 · similarity 0.88)
- Is Sarcasm Detection a Step-by-Step Reasoning Process in Large Language Models? (AAAI 2025 · similarity 0.87)
- MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
