用提示工程提升大模型情感分析与反语识别能力
Enhancing Sentiment Classification and Irony Detection in Large Language Models through Advanced Prompt Engineering Techniques
- 采用少样本、思维链等高级提示策略增强模型表现
- 思维链提示使gemini-1.5-flash反语识别准确率提升46%
- 不同模型需匹配特定提示策略，任务复杂度影响效果
本研究探讨了提示工程对大型语言模型（LLMs）在情感分析任务中的增强作用，重点关注GPT-4o-mini和gemini-1.5-flash。评估了少样本学习、思维链提示和自一致性等高级提示技术，并与基线方法对比。主要任务包括情感分类、基于方面的情感分析以及识别微妙语义如反语。通过准确率、召回率、精确率和F1分数评估模型性能。结果表明，高级提示显著提升情感分析效果：少样本提示在GPT-4o-mini上表现最优，而思维链提示使gemini-1.5-flash在反语检测中最高提升46%。这说明提示策略需根据模型架构和任务语义复杂度进行定制，强调提示设计与模型特性及任务需求的匹配性。
原文摘要 · Abstract (English)
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.
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。