TY  - JOUR
AU  - Hussain, Sayed Akif
AU  - Chen, Qiu-Shi
AU  - Hussain, Syed Amer
AU  - Hussain, Syed Atif
AU  - Komal, Asma
AU  - Khalid, Muhammad Imran
PY  - 2026
DA  - 2026/04/08
TI  - Improving Financial Forecasting with a Synergistic LLM-Transformer Architecture: A Hybrid Approach to Stock Price Prediction
JO  - ICCK Transactions on Intelligent Systematics
T2  - ICCK Transactions on Intelligent Systematics
JF  - ICCK Transactions on Intelligent Systematics
VL  - 3
IS  - 2
SP  - 70
EP  - 80
DO  - 10.62762/TIS.2025.976754
UR  - https://www.icck.org/article/abs/TIS.2025.976754
KW  - large language models
KW  - transformer
KW  - stock prediction
KW  - financial forecasting
KW  - time series
KW  - ablation study
AB  - This study proposes a novel hybrid deep learning framework that integrates a Large Language Model (LLM) with a Transformer architecture for stock price forecasting. The research addresses a critical theoretical gap in existing approaches that empirically combine textual and numerical data without a formal understanding of their interaction mechanisms. We conceptualize a prompt-based LLM as a mathematically defined signal generator, capable of extracting directional market sentiment and an associated confidence score from financial news. These signals are then dynamically fused with structured historical price features through a noise-robust gating mechanism, enabling the Transformer to adaptively weigh semantic and quantitative information. Empirical evaluations demonstrate that the proposed Hybrid LLM–Transformer model demonstrates promising improvement over a Vanilla Transformer baseline, reducing the Root Mean Squared Error (RMSE) by 5.28% (p = 0.003). Moreover, ablation and robustness analyses confirm the model’s stability under noisy conditions and its capacity to maintain interpretability through confidence-weighted attention. The findings contribute to theoretical exploration of LLM–Transformer interactions, offering a step toward explainable, noise-resilient, and semantically enriched financial forecasting systems.
SN  - 3068-5079
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Hussain2026Improving,
  author = {Sayed Akif Hussain and Qiu-Shi Chen and Syed Amer Hussain and Syed Atif Hussain and Asma Komal and Muhammad Imran Khalid},
  title = {Improving Financial Forecasting with a Synergistic LLM-Transformer Architecture: A Hybrid Approach to Stock Price Prediction},
  journal = {ICCK Transactions on Intelligent Systematics},
  year = {2026},
  volume = {3},
  number = {2},
  pages = {70-80},
  doi = {10.62762/TIS.2025.976754},
  url = {https://www.icck.org/article/abs/TIS.2025.976754},
  abstract = {This study proposes a novel hybrid deep learning framework that integrates a Large Language Model (LLM) with a Transformer architecture for stock price forecasting. The research addresses a critical theoretical gap in existing approaches that empirically combine textual and numerical data without a formal understanding of their interaction mechanisms. We conceptualize a prompt-based LLM as a mathematically defined signal generator, capable of extracting directional market sentiment and an associated confidence score from financial news. These signals are then dynamically fused with structured historical price features through a noise-robust gating mechanism, enabling the Transformer to adaptively weigh semantic and quantitative information. Empirical evaluations demonstrate that the proposed Hybrid LLM–Transformer model demonstrates promising improvement over a Vanilla Transformer baseline, reducing the Root Mean Squared Error (RMSE) by 5.28\% (p = 0.003). Moreover, ablation and robustness analyses confirm the model’s stability under noisy conditions and its capacity to maintain interpretability through confidence-weighted attention. The findings contribute to theoretical exploration of LLM–Transformer interactions, offering a step toward explainable, noise-resilient, and semantically enriched financial forecasting systems.},
  keywords = {large language models, transformer, stock prediction, financial forecasting, time series, ablation study},
  issn = {3068-5079},
  publisher = {Institute of Central Computation and Knowledge}
}