mlsanityData to 14 Oct 2026

Pragmatic Metacognitive Prompting Improves LLM Performance on Sarcasm Detection

arXiv 2412.04509 ↗First posted 4 Dec 2024cs.CLcited by 19

Not on the map. Why?

Abstract (arXiv)

Sarcasm detection is a significant challenge in sentiment analysis due to the nuanced and context-dependent nature of verbiage. We introduce Pragmatic Metacognitive Prompting (PMP) to improve the performance of Large Language Models (LLMs) in sarcasm detection, which leverages principles from pragmatics and reflection helping LLMs interpret implied meanings, consider contextual cues, and reflect on discrepancies to identify sarcasm. Using state-of-the-art LLMs such as LLaMA-3-8B, GPT-4o, and Claude 3.5 Sonnet, PMP achieves state-of-the-art performance on GPT-4o on MUStARD and SemEval2018. This study demonstrates that integrating pragmatic reasoning and metacognitive strategies into prompting significantly enhances LLMs' ability to detect sarcasm, offering a promising direction for future research in sentiment analysis.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 5 of its 28 references that are in the map. First posted on arXiv 4 Dec 2024.

Builds on

5 of 28 references.

References · 5

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2017Tensor Fusion Network for Multimodal Sentiment Analysiscited by 433
  5. 2023Sentiment Analysis in the Era of Large Language Models: A Reality Checkcited by 268

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 10.

19 papers.

Sort:

By area:

  1. 2025IMPersona: Evaluating Individual Level LM Impersonationcited by 11
  2. 2025Large Language Models for Subjective Language Understanding: A Surveycited by 9
  3. 2025What Makes a Good Natural Language Prompt?cited by 7
  4. 2025MUStReason: A Benchmark for Diagnosing Pragmatic Reasoning in Video-LMs for Multimodal Sarcasm Detectioncited by 5
  5. 2025Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Modelscited by 4
  6. 2025IRONIC: Coherence-Aware Reasoning Chains for Multi-Modal Sarcasm Detectioncited by 3
  7. 2026Rhetorical Questions in LLM Representations: A Linear Probing Studycited by 3
  8. 2025Context-Aware Pragmatic Metacognitive Prompting for Sarcasm Detectioncited by 2
  9. 2025Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniquescited by 1
  10. 2026Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responsescited by 1
  11. 2026Metacognition in LLMs: Foundations, Progress, and Opportunitiescited by 1
  12. 2025Nek Minit: Harnessing Pragmatic Metacognitive Prompting for Explainable Sarcasm Detection of Australian and Indian Englishcited by 0
7 more
  1. 2026Yor-Sarc: A gold-standard dataset for sarcasm detection in a low-resource African languagecited by 0
  2. 2026DRInQ: Evaluating Conversational Implicature with Controlled Context Variationcited by 0
  3. 2026Re-defining Humor Data Objects for AI Humor Researchcited by 0
  4. 2026The Register Gap: A Meaning Intelligence Framework for Nigerian Public Discoursecited by 0
  5. 2026Towards High-Level Semantic Intelligencecited by 0
  6. 2026Figurative and Cultural Knowledge in LLMs: Investigating Cross-Domain Transfer through Fine-Tuningcited by 0
  7. 2026Emo-Jev: Probabilistic Reasoning for Emotion Classification with Jevcited by 0