SILC-EFSA: Self-aware In-context Learning Correction for Entity-level Financial Sentiment Analysis

Senbin Zhu, Chenyuan He, Hongde Liu, Pengcheng Dong, Hanjie Zhao +4 more
12/26/2024
cs.CLcs.AIcs.CE

Official code: NLP-Bin/SILC-EFSA (4 stars, Apache-2.0, last commit 2024-09-14).

Abstract

In recent years, fine-grained sentiment analysis in finance has gained significant attention, but the scarcity of entity-level datasets remains a key challenge. To address this, we have constructed the largest English and Chinese financial entity-level sentiment analysis datasets to date. Building on this foundation, we propose a novel two-stage sentiment analysis approach called Self-aware In-context Learning Correction (SILC). The first stage involves fine-tuning a base large language model to generate pseudo-labeled data specific to our task. In the second stage, we train a correction model using a GNN-based example retriever, which is informed by the pseudo-labeled data. This two-stage strategy has allowed us to achieve state-of-the-art performance on the newly constructed datasets, advancing the field of financial sentiment analysis. In a case study, we demonstrate the enhanced practical utility of our data and methods in monitoring the cryptocurrency market. Our datasets and code are available at https://github.com/NLP-Bin/SILC-EFSA.

View on arXivView PDF

Code Implementations(1)

NLP-Bin/SILC-EFSAOfficial100%
Apache-2.0

SILC-EFSA: Self-aware In-context Learning Correction for Entity-Level Financial Sentiment Analysis

40Shell, PythonSep 2, 20242 years agoApache-2.0

Similar Papers

A Comparative Analysis of Fine-Tuned LLMs and Few-Shot Learning of LLMs for Financial Sentiment Analysis

85% match2023

Are Large Language Models Good In-context Learners for Financial Sentiment Analysis?

85% match2025

Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models

84% match2023

Chinese Fine-Grained Financial Sentiment Analysis with Large Language Models

83% match1 repo72023

Removing Non-Stationary Knowledge From Pre-Trained Language Models for Entity-Level Sentiment Classification in Finance

82% match2023

Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models

82% match1 repo21.3k2023

Cite this paper

@article{zhu2024silcefsa,
  title  = {SILC-EFSA: Self-aware In-context Learning Correction for Entity-level Financial Sentiment Analysis},
  author = {Senbin Zhu and Chenyuan He and Hongde Liu and Pengcheng Dong and Hanjie Zhao and Yuchen Yan and Yuxiang Jia and Hongying Zan and Min Peng},
  year   = {2024},
  eprint = {2412.19140},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.19140v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.19140.svg)](https://codeofpaper.com/paper/2412.19140)

Discussion