Improving In-Context Learning with Prediction Feedback for Sentiment Analysis

2024/06/05 by Hongling Xu, Xu, Hongling, Qianlong Wang +11 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Sentiment Analysis and Opinion Mining

paper · pdf · doi:10.48550/arxiv.2406.02911

openalex publication_date 2024/06/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Large language models (LLMs) have achieved promising results in sentiment analysis through the in-context learning (ICL) paradigm. However, their ability to distinguish subtle sentiments still remains a challenge. Inspired by the human ability to adjust understanding via feedback, this paper enhances ICL by incorporating prior predictions and feedback, aiming to rectify sentiment misinterpretation of LLMs. Specifically, the proposed framework consists of three steps: (1) acquiring prior predictions of LLMs, (2) devising predictive feedback based on correctness, and (3) leveraging a feedback-driven prompt to refine sentiment understanding. Experimental results across nine sentiment analysis datasets demonstrate the superiority of our framework over conventional ICL methods, with an average F1 improvement of 5.95%.

Cited by

• Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective

Related

• A Comprehensive Evaluation of Large Language Models on Aspect-Based Sentiment Analysis
• The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition
• Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps
• Multi-Task Learning with LLMs for Implicit Sentiment Analysis: Data-level and Task-level Automatic Weight Learning
• An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability