对比人类与大模型对表情包讽刺含义的理解差异。
Irony in Emojis: A Comparative Study of Human and LLM Interpretation
- 用GPT-4o评估表情包讽刺概率，对比人类判断。
- 发现大模型与人类在讽刺理解上存在一致与分歧。
- 揭示年龄性别等人口因素影响表情解读，也影响模型表现。
表情符号已成为在线交流中的通用语言，常携带微妙且依赖语境的含义。其中，讽刺因其表意与意图之间的不一致，对大型语言模型（LLMs）构成重大挑战。本研究考察GPT-4o对表情符号中讽刺意义的解读能力。通过提示GPT-4o评估特定表情符号在社交媒体上表达讽刺的可能性，并将其判断与人类感知进行对比，旨在缩小机器与人类理解之间的差距。研究发现，GPT-4o在讽刺理解方面展现出复杂而细致的能力，既与人类行为存在契合点，也存在明显分歧。此外，本研究还强调了年龄、性别等人口因素在表情符号解读中的重要性，并评估了这些因素如何影响GPT-4o的表现。
原文摘要 · Abstract (English)
Emojis have become a universal language in online communication, often carrying nuanced and context-dependent meanings. Among these, irony poses a significant challenge for Large Language Models (LLMs) due to its inherent incongruity between appearance and intent. This study examines the ability of GPT-4o to interpret irony in emojis. By prompting GPT-4o to evaluate the likelihood of specific emojis being used to express irony on social media and comparing its interpretations with human perceptions, we aim to bridge the gap between machine and human understanding. Our findings reveal nuanced insights into GPT-4o's interpretive capabilities, highlighting areas of alignment with and divergence from human behavior. Additionally, this research underscores the importance of demographic factors, such as age and gender, in shaping emoji interpretation and evaluates how these factors influence GPT-4o's performance.
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。