skip to main content
10.1145/3656766.3656798acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicbarConference Proceedingsconference-collections
research-article

Instruction fine-tuning based on Llama2-7b for news topic classification

Published: 01 June 2024 Publication History

Abstract

In the rapidly evolving financial sector, timely and accurate news classification is essential. This paper introduces an approach to enhance financial news topic classification using the Llama2-7b model, fine-tuned with the QLora algorithm. Our dataset, comprising 16,990 training samples and 4,117 test samples, is focused on financial news, categorized into 20 distinct themes. This work aims to leverage the advanced capabilities of Llama2-7b, combined with QLora's fine-tuning efficiency, to improve classification accuracy and efficiency in processing news. In our experiments, we compared the performance of Llama2-7b against several other models, including Roberta-Base, Roberta-Large, Deberta-Base, and Deberta-Large. The Llama2-7b model outperformed these models, achieving an accuracy of 0.8936, which is notably higher than Roberta-Large's 0.8810, Deberta-Large's 0.8832, and other benchmarks. These results underscore the effectiveness of Llama2-7b when fine-tuned with QLora, marking a significant advancement in the domain of financial news classification.

References

[1]
Piškorec, M., Antulov-Fantulin, N., Novak, P. K., Mozetič, I., Grčar, M., Vodenska, I., & Šmuc, T. 2014. Cohesiveness in financial news and its relation to market volatility. Scientific reports, 4(1), 5038.
[2]
Zhou, L., Wang, H., Zhang, L., Chen, E., & Chen, J. 2014. A novel knowledge network framework for financial news navigation. In Web-Age Information Management: 15th International Conference, WAIM 2014, Macau, China, June 16-18, 2014. Proceedings 15 (pp. 723-727). Springer International Publishing.
[3]
Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., ... & Kaplan, J. 2022. Constitutional ai: Harmlessness from ai feedback. arXiv preprint arXiv:2212.08073.
[4]
Chen, M., Tworek, J., Jun, H., Yuan, Q., de Oliveira Pinto, H. P., Kaplan, J., ... & Zaremba, W. (2021). Evaluating large language models trained on code. 2021. arXiv preprint arXiv:2107.03374.
[5]
Turney, P. D. 2002. Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. arXiv preprint cs/0212032.
[6]
Loughran, T., & McDonald, B. 2011. When is a liability not a liability? Textual analysis, dictionaries, and 10‐Ks. The Journal of finance, 66(1), 35-65.
[7]
Kearney, C., & Liu, S. 2014. Textual sentiment in finance: A survey of methods and models. International Review of Financial Analysis, 33, 171-185.
[8]
Dougal, C., Engelberg, J., Garcia, D., & Parsons, C. A. 2012. Journalists and the stock market. The Review of Financial Studies, 25(3), 639-679.
[9]
Wilson, T., Wiebe, J., & Hoffmann, P. 2009. Recognizing contextual polarity: An exploration of features for phrase-level sentiment analysis. Computational linguistics, 35(3), 399-433.
[10]
Malo, Pekka, Ankur Sinha, Pekka Korhonen, Jyrki Wallenius, and Pyry Takala. “Good debt or bad debt: Detecting semantic orientations in economic texts.” Journal of the Association for Information Science and Technology 65, no. 4:782-796, 2014.
[11]
Li, F. 2010. The information content of forward‐looking statements in corporate filings—A naïve Bayesian machine learning approach. Journal of Accounting Research, 48(5), 1049-1102.
[12]
Sousa, M. G., Sakiyama, K., de Souza Rodrigues, L., Moraes, P. H., Fernandes, E. R., & Matsubara, E. T. 2019, November. BERT for stock market sentiment analysis. In 2019 IEEE 31st international conference on tools with artificial intelligence (ICTAI) (pp. 1597-1601). IEEE.
[13]
[13] Zhao, L., Li, L., Zheng, X., & Zhang, J. 2021, May. A BERT based sentiment analysis and key entity detection approach for online financial texts. In 2021 IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD) (pp. 1233-1238). IEEE.

Index Terms

  1. Instruction fine-tuning based on Llama2-7b for news topic classification

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICBAR '23: Proceedings of the 2023 3rd International Conference on Big Data, Artificial Intelligence and Risk Management
    November 2023
    1156 pages
    ISBN:9798400716478
    DOI:10.1145/3656766
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 01 June 2024

    Permissions

    Request permissions for this article.

    Check for updates

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    ICBAR 2023

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 31
      Total Downloads
    • Downloads (Last 12 months)31
    • Downloads (Last 6 weeks)3
    Reflects downloads up to 20 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media