Is Sarcasm Detection A Step-by-Step Reasoning Process in Large Language Models?
Authors:
Preprint
Abstract
Elaborating a series of intermediate reasoning steps significantly improves the ability of large language models (LLMs) to solve complex problems, as such steps would evoke LLMs to think sequentially. However, human sarcasm understanding is often considered an intuitive and holistic cognitive process, in which various linguistic, contextual, and emotional cues are integrated to form a comprehensive understanding of the speaker's true intention, which is argued not be limited to a step-by-step reasoning process. To verify this argument, we introduce a new prompting framework called SarcasmCue, which contains four prompting strategies, $viz.$ chain of contradiction (CoC), graph of cues (GoC), bagging of cues (BoC) and tensor of cues (ToC), which elicits LLMs to detect human sarcasm by considering sequential and non-sequential prompting methods. Through a comprehensive empirical comparison on four benchmarking datasets, we show that the proposed four prompting methods outperforms standard IO prompting, CoT and ToT with a considerable margin, and non-sequential prompting generally outperforms sequential prompting.
Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Structured Chain-of-Thought Prompting for Code GenerationACM Transactions on Software Engineering and Methodology, 2025
- BNS-Net: A Dual-Channel Sarcasm Detection Method Considering Behavior-Level and Sentence-Level Conflicts2024
- Active Prompting with Chain-of-Thought for Large Language Models2024
- KnowleNet: Knowledge fusion network for multimodal sarcasm detectionInformation Fusion, 2023
- A Quantum Probability Driven Framework for Joint Multi-Modal Sarcasm, Sentiment and Emotion AnalysisIEEE Transactions on Affective Computing, 2023
- Stance-level Sarcasm Detection with BERT and Stance-centered Graph Attention NetworksACM Transactions on Internet Technology, 2023
- Dynamic Routing Transformer Network for Multimodal Sarcasm Detection2023
- A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict2022
- Sarcasm detection in mash-up language using soft-attention based bi-directional LSTM and feature-rich CNNApplied Soft Computing, 2020
- Sarcasm Analysis Using Conversation ContextComputational Linguistics, 2018