Pith. sign in

REVIEW 5 cited by

Financial Sentiment Analysis on News and Reports Using Large Language Models and FinBERT

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.01987 v1 pith:GNAV3TXH submitted 2024-10-02 cs.IR cs.CLcs.SIq-fin.GN

Yanxin Shen , Pulin Kirin Zhang This is my paper · ORCID
classification cs.IRcs.CLcs.SIq-fin.GN
keywords financialsentimentfinbertanalysisfew-shotlanguagelargellms
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Financial sentiment analysis (FSA) is crucial for evaluating market sentiment and making well-informed financial decisions. The advent of large language models (LLMs) such as BERT and its financial variant, FinBERT, has notably enhanced sentiment analysis capabilities. This paper investigates the application of LLMs and FinBERT for FSA, comparing their performance on news articles, financial reports and company announcements. The study emphasizes the advantages of prompt engineering with zero-shot and few-shot strategy to improve sentiment classification accuracy. Experimental results indicate that GPT-4o, with few-shot examples of financial texts, can be as competent as a well fine-tuned FinBERT in this specialized field.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Zero-Shot End-to-End Relation Extraction in Chinese: A Comparative Study of Gemini, LLaMA and ChatGPT

    cs.CL 2025-02 conditional novelty 4.0 of 10

    In a zero-shot Chinese relation extraction test on DuIE 2.0, gpt-4-turbo achieved the best F1 at 0.367, Gemini flash models were fastest, and LLaMA models performed worst.

  2. Comparative Analysis of Listwise Reranking with Large Language Models in Limited-Resource Language Contexts

    cs.CL 2024-12 reject novelty 3.0 of 10

    A benchmark study reports that RankGPT-style LLM rerankers beat BM25 on Hausa, Somali, Swahili, and Yoruba retrieval, but without statistical support or released code.

  3. Privacy-Preserving Hybrid Ensemble Model for Network Anomaly Detection: Balancing Security and Data Protection

    cs.LG 2025-02 reject novelty 2.0 of 10

    A stacking ensemble of KNN, SVM, XGBoost, and ANN is claimed to reach 94.3% accuracy on network anomaly detection, but no dataset, code, or privacy analysis is provided.

  4. Robustness of Large Language Models Against Adversarial Attacks

    cs.CL 2024-12 reject novelty 2.0 of 10

    An empirical evaluation reports that GPT-4o is the most robust to character-level and jailbreak attacks, but the paper's analysis contradicts its own tables and the jailbreak metric is undefined.

  5. Financial News-Driven LLM Reinforcement Learning for Portfolio Management

    q-fin.CP 2024-11 reject novelty 2.0 of 10

    In a one-year backtest, adding LLM-generated news sentiment to a PPO trading agent increased average net worth versus plain RL and beat buy-and-hold on the LEXCX portfolio.

Pith tools