提示即一切：基于多视角提示的大语言模型在方面级情感分析中的应用
Prompting Is All You Need: Multi-view Prompting Large Language Models for Aspect-Based Sentiment Analysis
AI总结：
提出LLM-MvP方法，通过多视角提示、模式约束解码和前缀批处理，使大语言模型在少量样本下达到与微调模型竞争甚至更优的性能，同时降低计算开销。
摘要：
近期工作探索了大语言模型（LLMs）在方面级情感分析（ABSA）中通过少样本提示的能力，相比零样本基线显著改进，且所需标注示例大幅减少。然而，与在数百个示例上微调的模型相比仍存在性能差距，且LLM推理的计算成本对部署构成实际障碍。我们提出了基于LLM的多视角提示（LLM-MvP），将考虑多种元素排序的多视角原理适配到LLM提示中。通过将模式约束解码与上下文无关语法及前缀批处理相结合，LLM-MvP实现了与微调方法竞争甚至更优的性能，同时大幅降低计算开销。在五个基准数据集上的广泛实验表明，LLM-MvP缩小了少样本提示与微调模型之间的差距，为ABSA提供了实用且高效的解决方案。
英文摘要：
Recent work explored the capabilities of Large Language Models (LLMs) in Aspect-Based Sentiment Analysis (ABSA) through few-shot prompting, requiring substantially fewer annotated examples while achieving notable improvements over zero-shot baselines. However, a performance gap remained compared to models fine-tuned on hundreds of examples, and the computational costs of LLM inference present practical barriers to deployment. We introduce LLM-based Multi-View Prompting (LLM-MvP), which adapts the multi-view principle of considering multiple element orderings to LLM prompting. By combining schema-constrained decoding with a context-free grammar and prefix batching, LLM-MvP achieves performance competitive or superior to fine-tuned approaches while substantially reducing computational overhead. Extensive experiments across five benchmark datasets demonstrate that LLM-MvP closes the gap between few-shot prompting and fine-tuned models, offering a practical and efficient solution for ABSA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
