Pragmatic Metacognitive Prompting Improves LLM Performance on Sarcasm Detection
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
The Register Gap: A Meaning Intelligence Framework for Nigerian Public Discourse
The Meaning Intelligence Framework raises zero-shot register classification accuracy from 33.3% to 73.3% on a 30-item Nigerian discourse calibration set while showing that smaller models can outperform larger ones on ...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.