用多视角提示让大模型高效精准做情感分析。
Prompting Is All You Need: Multi-view Prompting Large Language Models for Aspect-Based Sentiment Analysis
- 设计多视角提示策略，通过不同顺序输入提升模型理解力。
- 在五个数据集上表现媲美微调模型，且推理成本更低。
- 适合资源有限但需高精度情感分析的场景。
近期研究通过少样本提示（few-shot prompting）探索大语言模型（LLM）在方面级情感分析（ABSA）中的能力，仅需少量标注样本即可显著超越零样本基线。然而，与在数百个样本上微调的模型相比仍存在性能差距，且LLM推理的计算开销限制了实际部署。本文提出基于大模型的多视角提示（LLM-MvP），将多视角思想引入提示设计，通过模式约束解码、无上下文语法和前缀批处理，在保持高性能的同时大幅降低计算负担。在五个基准数据集上的大量实验表明，LLM-MvP缩小了少样本提示与微调模型之间的差距，为ABSA提供了一种高效实用的解决方案。
原文摘要 · Abstract (English)
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.
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。