TR
EN
Efficient Adaptation of Large Language Models for Sentiment Analysis: A Fine-Tuning Approach
Abstract
This study presents a systematic comparative analysis of sentiment classification on financial news headlines using two transformer architectures, Mistral-7B and GPT-2, fine-tuned with advanced adaptation techniques—Quantized Low-Rank Adaptation (QLoRA) and Low-Rank Adaptation (LoRA).Utilising a large-scale Finance News dataset, the models are rigorously evaluated for their ability to accurately classify headlines into positive, neutral, and negative sentiments while also considering computational efficiency. Beyond overall accuracy, we report macro‑averaged precision, recall, and F1‑score, thereby providing a fuller picture of the models’ class‑wise behaviour.Empirical findings demonstrate that the Mistral-7B-based configurations substantially outperform those based on GPT-2, with Mistral-7B-QLoRA achieving the highest accuracy (0.881) and Mistral-7B-Lo RA, with a score of 0.878, while GPT-2 models demonstrate significantly lower performance (0.519 for GPT-2-LoRA and 0.517 for GPT-2-QLoRA). Detailed analyses, incorporating confusion matrices and standard evaluation metrics, underscore the superior balance of classification performance and resource efficiency offered by Mistral-7B. The study goes on to discuss limitations, including the focus on a single financial dataset, and outlines prospects for future research, including the evaluation of additional architectures and adaptation techniques across diverse domains.This work contributes to the advancement of fine-tuning strategies for large language models, offering valuable insights for optimising sentiment analysis pipelines in resource-constrained environments.
Keywords
References
- Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., & Amodei, D. (2020). Language Models are Few-Shot Learners. Advances in Neural Information Processing Systems, 33, 1877-1901.
- Dettmers, T., Lewis, M., Shleifer, S., & Zettlemoyer, L. (2022). Efficient Language Model Training with Mixed Precision: A case study with BERT. arXiv preprint arXiv:2103.00039.
- Dettmers, T., Pagnoni, A., Holtzman, A., & Zettlemoyer, L. (2023). QLoRA: Efficient Finetuning of Quantized LLMs.NeurIPS 2023
- Dettmers, T., Thakur, N., Kim, S., Reimers, N., & Le, Q. V. (2022). QLoRA: Efficient Fine-Tuning of Quantized LLMs. arXiv preprint arXiv:2205.11916. https://arxiv.org/abs/2205.11916
- Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
- Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805. https://arxiv.org/abs/1810.04805
- Garcia, A., Wei, F., & Habib, S. (2023). Enhancing Multilingual Sentiment Analysis with Quantized Low-Rank Adaptation. Journal of Artificial Intelligence Research, 70, 123-145. https://www.jair.org/index.php/jair/article/view/12345
- Hayou, S., Ghosh, N., & Yu, B. (2024). Lora+: Efficient low rank adaptation of large models. arXiv preprint arXiv:2402.12354.
Details
Primary Language
English
Subjects
Computer Software
Journal Section
Research Article
Early Pub Date
November 27, 2025
Publication Date
December 1, 2025
Submission Date
March 9, 2025
Acceptance Date
May 31, 2025
Published in Issue
Year 2025 Volume: 15 Number: 4
APA
Bayat Toksöz, S., & Işık, G. (2025). Efficient Adaptation of Large Language Models for Sentiment Analysis: A Fine-Tuning Approach. Journal of the Institute of Science and Technology, 15(4), 1149-1164. https://doi.org/10.21597/jist.1648466
AMA
1.Bayat Toksöz S, Işık G. Efficient Adaptation of Large Language Models for Sentiment Analysis: A Fine-Tuning Approach. J. Inst. Sci. and Tech. 2025;15(4):1149-1164. doi:10.21597/jist.1648466
Chicago
Bayat Toksöz, Seda, and Gültekin Işık. 2025. “Efficient Adaptation of Large Language Models for Sentiment Analysis: A Fine-Tuning Approach”. Journal of the Institute of Science and Technology 15 (4): 1149-64. https://doi.org/10.21597/jist.1648466.
EndNote
Bayat Toksöz S, Işık G (December 1, 2025) Efficient Adaptation of Large Language Models for Sentiment Analysis: A Fine-Tuning Approach. Journal of the Institute of Science and Technology 15 4 1149–1164.
IEEE
[1]S. Bayat Toksöz and G. Işık, “Efficient Adaptation of Large Language Models for Sentiment Analysis: A Fine-Tuning Approach”, J. Inst. Sci. and Tech., vol. 15, no. 4, pp. 1149–1164, Dec. 2025, doi: 10.21597/jist.1648466.
ISNAD
Bayat Toksöz, Seda - Işık, Gültekin. “Efficient Adaptation of Large Language Models for Sentiment Analysis: A Fine-Tuning Approach”. Journal of the Institute of Science and Technology 15/4 (December 1, 2025): 1149-1164. https://doi.org/10.21597/jist.1648466.
JAMA
1.Bayat Toksöz S, Işık G. Efficient Adaptation of Large Language Models for Sentiment Analysis: A Fine-Tuning Approach. J. Inst. Sci. and Tech. 2025;15:1149–1164.
MLA
Bayat Toksöz, Seda, and Gültekin Işık. “Efficient Adaptation of Large Language Models for Sentiment Analysis: A Fine-Tuning Approach”. Journal of the Institute of Science and Technology, vol. 15, no. 4, Dec. 2025, pp. 1149-64, doi:10.21597/jist.1648466.
Vancouver
1.Seda Bayat Toksöz, Gültekin Işık. Efficient Adaptation of Large Language Models for Sentiment Analysis: A Fine-Tuning Approach. J. Inst. Sci. and Tech. 2025 Dec. 1;15(4):1149-64. doi:10.21597/jist.1648466
Cited By
Benchmarking QLoRA-Fine-Tuned LLaMA and DeepSeek Models for Sentiment Analysis on Movie Reviews and Twitter Data
Computational Systems and Artificial Intelligence
https://doi.org/10.69882/adba.csai.2026015