通过引导模型反思语境与言外之意，提升对讽刺的识别能力。
Pragmatic Metacognitive Prompting Improves LLM Performance on Sarcasm Detection
- 引入基于语用学和元认知的提示策略，增强模型对隐含意义的理解。
- 在MUStARD和SemEval2018数据集上达到当前最优性能。
- 适合研究情感分析、对话理解及模型推理能力的学者参考。
讽刺检测因语言的细微差异和强上下文依赖性，在情感分析中极具挑战。本文提出实用型元认知提示（Pragmatic Metacognitive Prompting, PMP），利用语用学原理与反思机制，帮助大语言模型（LLMs）理解隐含含义、关注上下文线索，并识别语义矛盾以检测讽刺。实验使用LLaMA-3-8B、GPT-4o和Claude 3.5 Sonnet等先进模型，在MUStARD和SemEval2018数据集上验证了PMP的有效性，结果显示其在GPT-4o上的表现达到当前最优水平。该研究证明，将语用推理与元认知策略融入提示设计，显著提升了大模型对讽刺的识别能力，为未来情感分析研究提供了新方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。