用预训练模型分析情绪，发现结构化提示和分组能显著提升效果。
Unraveling Emotions with Pre-Trained Models
- 对比微调与提示工程在情绪识别中的表现
- 微调模型准确率超70%，提示工程需结构化设计
- 适合需要精准情绪分析的应用场景
Transformer模型在情绪识别领域取得显著进展，但针对大语言模型（LLMs）的开放式查询仍存在挑战。现有模型虽表现良好，但在开放文本中进行自动情绪分析仍面临上下文歧义、语言多样性及复杂情感表达难以解读等问题。为应对这些局限，本文比较了微调与提示工程在三种情境下的有效性：(i) 微调预训练模型与通用LLM使用简单提示的表现；(ii) 不同情绪提示设计对LLM的影响；(iii) 情绪分组技术对模型性能的作用。实验结果显示，微调后的预训练模型在情绪识别任务中达到70%以上的准确率。研究还表明，LLM需通过结构化提示工程和情绪分组策略才能有效提升性能。该成果有助于改善情感分析、人机交互及用户行为理解。
原文摘要 · Abstract (English)
Transformer models have significantly advanced the field of emotion recognition. However, there are still open challenges when exploring open-ended queries for Large Language Models (LLMs). Although current models offer good results, automatic emotion analysis in open texts presents significant challenges, such as contextual ambiguity, linguistic variability, and difficulty interpreting complex emotional expressions. These limitations make the direct application of generalist models difficult. Accordingly, this work compares the effectiveness of fine-tuning and prompt engineering in emotion detection in three distinct scenarios: (i) performance of fine-tuned pre-trained models and general-purpose LLMs using simple prompts; (ii) effectiveness of different emotion prompt designs with LLMs; and (iii) impact of emotion grouping techniques on these models. Experimental tests attain metrics above 70% with a fine-tuned pre-trained model for emotion recognition. Moreover, the findings highlight that LLMs require structured prompt engineering and emotion grouping to enhance their performance. These advancements improve sentiment analysis, human-computer interaction, and understanding of user behavior across various domains.
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。