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

arXiv: https://arxiv.org/abs/2601.08302 · HTML: https://mlsanity.com/paper/2601.08302/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Builds on (most cited first, 11 of 11)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought](https://mlsanity.com/paper/2502.21212/) (2025)
- [SarcasmBench: Towards Evaluating Large Language Models on Sarcasm Understanding](https://mlsanity.com/paper/2408.11319/) (2024)
- [Is Sarcasm Detection A Step-by-Step Reasoning Process in Large Language Models?](https://mlsanity.com/paper/2407.12725/) (2024)
- [Pre-trained Large Language Models for Financial Sentiment Analysis](https://mlsanity.com/paper/2401.05215/) (2024)
- [A Comprehensive Evaluation of Large Language Models on Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2412.02279/) (2024)
- [LLMs for Targeted Sentiment in News Headlines: Exploring the Descriptive-Prescriptive Dilemma](https://mlsanity.com/paper/2403.00418/) (2024)

## Abstract (arXiv)

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.