用大模型零样本做多语言情感分析，发现简单提示更有效
Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Models
- 直接用大模型零样本处理多语言情感分析任务
- 简单提示比复杂推理策略在高资源语言中表现更好
- 适合对少标注数据场景下快速部署的开发者参考
基于方面的情感分析（ABSA）是一种序列标注任务，在多语言环境中日益受到关注。以往研究主要集中在为ABSA微调或训练专用模型，而本文评估大语言模型（LLMs）在零样本条件下的表现，探索其在极少任务适配下的潜力。我们在九种不同模型上对多语言ABSA任务进行了全面实证评估，考察了包括原始零样本、思维链（CoT）、自我改进、自我辩论和自我一致性在内的多种提示策略。结果表明，尽管大模型在多语言ABSA中展现出潜力，但整体仍逊于经过微调的任务专用模型。值得注意的是，简单零样本提示在英语等高资源语言中往往优于复杂策略。这些发现强调了进一步优化基于大模型的方法以有效应对跨语言ABSA任务的必要性。
原文摘要 · Abstract (English)
Aspect-based sentiment analysis (ABSA), a sequence labeling task, has attracted increasing attention in multilingual contexts. While previous research has focused largely on fine-tuning or training models specifically for ABSA, we evaluate large language models (LLMs) under zero-shot conditions to explore their potential to tackle this challenge with minimal task-specific adaptation. We conduct a comprehensive empirical evaluation of a series of LLMs on multilingual ABSA tasks, investigating various prompting strategies, including vanilla zero-shot, chain-of-thought (CoT), self-improvement, self-debate, and self-consistency, across nine different models. Results indicate that while LLMs show promise in handling multilingual ABSA, they generally fall short of fine-tuned, task-specific models. Notably, simpler zero-shot prompts often outperform more complex strategies, especially in high-resource languages like English. These findings underscore the need for further refinement of LLM-based approaches to effectively address ABSA task across diverse languages.
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。