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%.
Anthology ID:
2024.findings-acl.232
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3879–3890
Language:
URL:
https://aclanthology.org/2024.findings-acl.232
DOI:
Bibkey:
Cite (ACL):
Hongling Xu, Qianlong Wang, Yice Zhang, Min Yang, Xi Zeng, Bing Qin, and Ruifeng Xu. 2024. Improving In-Context Learning with Prediction Feedback for Sentiment Analysis. In Findings of the Association for Computational Linguistics ACL 2024, pages 3879–3890, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Improving In-Context Learning with Prediction Feedback for Sentiment Analysis (Xu et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.232.pdf