Improving In-Context Learning with Prediction Feedback for Sentiment Analysis
Hongling Xu, Qianlong Wang, Yice Zhang, Min Yang, Xi Zeng, Bing Qin, Ruifeng Xu
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%.
BibTeX
@inproceedings{xu-etal-2024-improving,
title = "Improving In-Context Learning with Prediction Feedback for Sentiment Analysis",
author = "Xu, Hongling and
Wang, Qianlong and
Zhang, Yice and
Yang, Min and
Zeng, Xi and
Qin, Bing and
Xu, Ruifeng",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.232/",
doi = "10.18653/v1/2024.findings-acl.232",
pages = "3879--3890"
}