CFMS: Towards Explainable and Fine-Grained Chinese Multimodal Sarcasm Detection Benchmark

• URL: http://arxiv.org/abs/2604.16372v1
• Date: Mon, 23 Mar 2026 15:55:14 GMT
• Title: CFMS: Towards Explainable and Fine-Grained Chinese Multimodal Sarcasm Detection Benchmark
• Abstract summary: We construct CFMS, the first fine-grained multimodal sarcasm dataset tailored for Chinese social media.<n>We find that the fine-grained explanation annotations effectively guide AI in generating images with explicit sarcastic intent.<n>To overcome the constraints of traditional retrieval methods, we propose a Reinforcement Learning-augmented In-Context Learning strategy.
• Score: 11.646782931569026
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal sarcasm detection has recently garnered significant attention. However, existing benchmarks suffer from coarse-grained annotations and limited cultural coverage, which hinder research into fine-grained semantic understanding. To address this, we construct CFMS, the first fine-grained multimodal sarcasm dataset tailored for Chinese social media. It comprises 2,796 high-quality image-text pairs and provides a triple-level annotation framework: sarcasm identification, target recognition, and explanation generation. We find that the fine-grained explanation annotations effectively guide AI in generating images with explicit sarcastic intent. Furthermore, we curate a high-consistency parallel Chinese-English metaphor subset (200 entries each), revealing significant limitations of current models in metaphoric reasoning. To overcome the constraints of traditional retrieval methods, we propose a Reinforcement Learning-augmented In-Context Learning strategy (PGDS) to dynamically optimize exemplar selection. Extensive experiments demonstrate that CFMS provides a solid foundation for building reliable multimodal sarcasm understanding systems, and the PGDS method significantly outperforms existing baselines on key tasks. Our data and code are available at https://anonymous.4open.science/r/CFMS-E8F9.

Related papers

• Achieving Text-based Person Retrieval with Any Granularity [80.69427598925718]
  This paper introduces a new paradigm, Text-based Person Retrieval with Any Granularity.<n>We formalize a five-level granularity spectrum and construct UFine6926-MG, a high-quality multi-grained annotated dataset.<n>We then propose the Cross-modal Multi-grained Aligning and Matching framework.
  arXiv  Detail & Related papers  (2026-07-23T08:42:25Z)
• Reasoning-Aware AIGC Detection via Alignment and Reinforcement [55.09684020007737]
  REVEAL is a framework that generates interpretable reasoning chains before classification.<n>It achieves state-of-the-art performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2026-04-21T07:29:55Z)
• GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification [26.21876180083083]
  GRASP is a framework that integrates visual grounding with explicit Chain-of-Thought (CoT) reasoning to move beyond black-box MSTI.<n>We introduce Grounded CoT reasoning, which explicitly anchors sarcasm-related visual regions within the reasoning trajectory.<n>Our dataset and source code will be released on GitHub.
  arXiv  Detail & Related papers  (2026-04-10T02:38:14Z)
• Context-Aware Pragmatic Metacognitive Prompting for Sarcasm Detection [0.0]
  Currently, Pre-trained Language Models (PLMs) and Large Language Models (LLMs) are the preferred approach for sarcasm detection.<n>We introduce a retrieval-aware approach that incorporates retrieved contextual information for each target text.<n>Non-parametric retrieval resulted in a significant 9.87% macro-F1 improvement on Twitter Indonesia Sarcastic compared to the original PMP method.
  arXiv  Detail & Related papers  (2025-11-26T05:19:31Z)
• Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions [81.33113485830711]
  We introduce a vision-free, single-encoder retrieval pipeline for vision-language models.<n>We migrate to a text-to-text paradigm with the assistance of VLLM-generated structured image descriptions.<n>Our approach achieves state-of-the-art zero-shot performance on multiple retrieval and compositionality benchmarks.
  arXiv  Detail & Related papers  (2025-09-23T16:22:27Z)
• Can Large Vision-Language Models Understand Multimodal Sarcasm? [14.863320201956963]
  Sarcasm is a complex linguistic phenomenon that involves a disparity between literal and intended meanings.<n>We evaluate Large Visual Language Models (LVLMs) in Multimodal Sarcasm Analysis (MSA) tasks.<n>We propose a training-free framework that integrates in-depth object extraction and external conceptual knowledge.
  arXiv  Detail & Related papers  (2025-08-05T17:05:11Z)
• METER: Multi-modal Evidence-based Thinking and Explainable Reasoning -- Algorithm and Benchmark [48.78602579128459]
  We introduce METER, a unified benchmark for interpretable forgery detection spanning images, videos, audio, and audio-visual content.<n>Our dataset comprises four tracks, each requiring not only real-vs-fake classification but also evidence-chain-based explanations.
  arXiv  Detail & Related papers  (2025-07-22T03:42:51Z)
• Towards General Visual-Linguistic Face Forgery Detection(V2) [90.6600794602029]
  Face manipulation techniques have achieved significant advances, presenting serious challenges to security and social trust.<n>Recent works demonstrate that leveraging multimodal models can enhance the generalization and interpretability of face forgery detection.<n>We propose Face Forgery Text Generator (FFTG), a novel annotation pipeline that generates accurate text descriptions by leveraging forgery masks for initial region and type identification.
  arXiv  Detail & Related papers  (2025-02-28T04:15:36Z)
• Binary Code Similarity Detection via Graph Contrastive Learning on Intermediate Representations [52.34030226129628]
  Binary Code Similarity Detection (BCSD) plays a crucial role in numerous fields, including vulnerability detection, malware analysis, and code reuse identification. In this paper, we propose IRBinDiff, which mitigates compilation differences by leveraging LLVM-IR with higher-level semantic abstraction. Our extensive experiments, conducted under varied compilation settings, demonstrate that IRBinDiff outperforms other leading BCSD methods in both One-to-one comparison and One-to-many search scenarios.
  arXiv  Detail & Related papers  (2024-10-24T09:09:20Z)
• Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation [53.97962603641629]
  We propose a novel mulTi-source sEmantic grAph-based Multimodal sarcasm explanation scheme, named TEAM. TEAM extracts the object-level semantic meta-data instead of the traditional global visual features from the input image. TEAM introduces a multi-source semantic graph that comprehensively characterize the multi-source semantic relations.
  arXiv  Detail & Related papers  (2023-06-29T03:26:10Z)
• Multi-modal Sarcasm Detection and Humor Classification in Code-mixed Conversations [14.852199996061287]
  We develop a Hindi-English code-mixed dataset, MaSaC, for the multi-modal sarcasm detection and humor classification in conversational dialog. We propose MSH-COMICS, a novel attention-rich neural architecture for the utterance classification.
  arXiv  Detail & Related papers  (2021-05-20T18:33:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.