mlsanityData to 14 Oct 2026

IRONIC: Coherence-Aware Reasoning Chains for Multi-Modal Sarcasm Detection

arXiv 2505.16258 ↗First posted 22 May 2025cs.CL cs.AI cs.CVcited by 3

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

Interpreting figurative language such as sarcasm across multi-modal inputs presents unique challenges, often requiring task-specific fine-tuning and extensive reasoning steps. However, current Chain-of-Thought approaches do not efficiently leverage the same cognitive processes that enable humans to identify sarcasm. We present IRONIC, an in-context learning framework that leverages Multi-modal Coherence Relations to analyze referential, analogical and pragmatic image-text linkages. Our experiments show that IRONIC achieves state-of-the-art performance on zero-shot Multi-modal Sarcasm Detection across different baselines. This demonstrates the need for incorporating linguistic and cognitive insights into the design of multi-modal reasoning strategies. Our code is available at: https://github.com/aashish2000/IRONIC

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 24 of its 38 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

24 of 38 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models3 Mar
  2. 2025CORDIAL: Can Multimodal Large Language Models Effectively Understand Coherence Relationships?16 Feb
  3. 2024Is Sarcasm Detection A Step-by-Step Reasoning Process in Large Language Models?17 Jul

Other references · 21

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  4. 2024Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMscited by 735
  5. 2019Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)cited by 174
  6. 2021FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimizationcited by 71
  7. 2023Metacognitive Prompting Improves Understanding in Large Language Modelscited by 58
  8. 2016Detecting Sarcasm in Multimodal Social Platformscited by 44
  9. 2024RATT: A Thought Structure for Coherent and Correct LLM Reasoningcited by 41
  10. 2022When did you become so smart, oh wise one?! Sarcasm Explanation in Multi-modal Multi-party Dialoguescited by 33
  11. 2023MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection Systemcited by 31
  12. 2022A Multimodal Corpus for Emotion Recognition in Sarcasmcited by 29
9 more
  1. 2020Clue: Cross-modal Coherence Modeling for Caption Generationcited by 24
  2. 2020Diverse Image Captioning with Context-Object Split Latent Spacescited by 22
  3. 2024Pragmatic Metacognitive Prompting Improves LLM Performance on Sarcasm Detectioncited by 19
  4. 2023Debiasing Multimodal Sarcasm Detection with Contrastive Learningcited by 13
  5. 2023Understanding Social Media Cross-Modality Discourse in Linguistic Spacecited by 6
  6. 2021Cross-Modal Coherence for Text-to-Image Retrievalcited by 5
  7. 2023ANNA: Abstractive Text-to-Image Synthesis with Filtered News Captionscited by 5
  8. 2025RONA: Pragmatically Diverse Image Captioning with Coherence Relationscited by 3
  9. 2025Commander-GPT: Fully Unleashing the Sarcasm Detection Capability of Multi-Modal Large Language Modelscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025SEVADE: Self-Evolving Multi-Agent Analysis with Decoupled Evaluation for Hallucination-Resistant Irony Detectioncited by 2
  2. 2026ProCrit: Self-Elicited Multi-Perspective Reasoning with Critic-Guided Revision for Multimodal Sarcasm Detectioncited by 0
  3. 2026PragMatch: Separating Pragmatic Incongruity from Cross-Modal Mismatch in Large Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Think Twice Before You Judge: Mixture of Dual Reasoning Experts for Multimodal Sarcasm Detection
  2. 2024CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models
  3. 2025Evaluating Open-Source Vision-Language Models for Multimodal Sarcasm Detection
  4. 2025MUStReason: A Benchmark for Diagnosing Pragmatic Reasoning in Video-LMs for Multimodal Sarcasm Detection
  5. 2026MuVaC: A Variational Causal Framework for Multimodal Sarcasm Understanding in Dialogues
  6. 2025Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models
  7. 2025MMSD3.0: A Multi-Image Benchmark for Real-World Multimodal Sarcasm Detection
  8. 2025Irony Detection, Reasoning and Understanding in Zero-shot Learning