Prompting Is All You Need: Multi-view Prompting Large Language Models for Aspect-Based Sentiment Analysis

2026-05-27

AI Summary

This work addresses the significant performance gap between few-shot prompting and fine-tuning approaches in aspect-based sentiment analysis (ABSA) using large language models (LLMs), as well as the high inference overhead of current prompting methods. To bridge this gap without requiring model fine-tuning, the authors propose LLM-MvP, a novel multi-view prompting framework that integrates context-free grammar-constrained decoding with prefix batching. This approach, for the first time, incorporates multi-view reasoning into prompt design to enhance prediction accuracy while substantially reducing computational costs. Experimental results across five benchmark datasets demonstrate that LLM-MvP markedly narrows the performance disparity between few-shot prompting and fine-tuned models—and even surpasses them in certain settings—while significantly lowering inference overhead, thereby advancing efficient and practical ABSA with LLMs.

Abstract

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.

Problem

• Aspect-Based Sentiment Analysis
• Large Language Models
• Few-shot Prompting
• Computational Cost
• Performance Gap

Innovation

• Multi-View Prompting
• Aspect-Based Sentiment Analysis
• Large Language Models
• Schema-Constrained Decoding
• Prefix Batching