Enhancing Sentiment Classification and Irony Detection in Large Language Models through Advanced Prompt Engineering Techniques

TL;DR

This paper explores advanced prompt engineering techniques to improve sentiment classification and irony detection in large language models, demonstrating significant performance gains through tailored prompting strategies.

Contribution

It introduces and evaluates specific prompt engineering methods like few-shot and chain-of-thought prompting, showing their effectiveness varies by model and task.

Findings

Few-shot prompting improves GPT-4o-mini sentiment analysis.

Chain-of-thought prompting enhances irony detection in gemini-1.5-flash.

Prompt strategies should be tailored to model and task complexity.

Abstract

This study investigates the use of prompt engineering to enhance large language models (LLMs), specifically GPT-4o-mini and gemini-1.5-flash, in sentiment analysis tasks. It evaluates advanced prompting techniques like few-shot learning, chain-of-thought prompting, and self-consistency against a baseline. Key tasks include sentiment classification, aspect-based sentiment analysis, and detecting subtle nuances such as irony. The research details the theoretical background, datasets, and methods used, assessing performance of LLMs as measured by accuracy, recall, precision, and F1 score. Findings reveal that advanced prompting significantly improves sentiment analysis, with the few-shot approach excelling in GPT-4o-mini and chain-of-thought prompting boosting irony detection in gemini-1.5-flash by up to 46%. Thus, while advanced prompting techniques overall improve performance, the fact that few-shot prompting works best for GPT-4o-mini and chain-of-thought excels in gemini-1.5-flash for irony detection suggests that prompting strategies must be tailored to both the model and the task. This highlights the importance of aligning prompt design with both the LLM's architecture and the semantic complexity of the task.