Skip to main content

2025 | OriginalPaper | Buchkapitel

A Systematic Analysis of Diverse Large Language Models and Their Operational Paradigm

verfasst von : Omkar Bhattarai, Raj Chaudhary, Rahul Kumar, Ali Imam Abidi

Erschienen in: Innovative Computing and Communications

Verlag: Springer Nature Singapore

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

LLMs (Large Language Models) generated texts (e.g. Texts generated by Chat GPT) and its use has been growing rapidly where any language-related problems can be solved or any queries based on language translation can be answered easily. Some of the most well-known LLMs include OpenAI’s GPT models (GPT1, 2, 3.5, 4), Google’s BARD, BERT, Facebook’s RoBERTa and so on. Since natural language text is generated by such LLMs, it has the several possible issues associated with it. For example, our creativity will be faded away as all the ideas, codes and solutions are generated by these models. Therefore, accurate and efficient classifier tool is necessary to be formulated and implemented. Before developing a classifier tool, review of various LLMs will be done so that actual working of the large language models can be identified and used for further analysis of classifier model. LLM research has recently made tremendous strides in both academia and business industry, with ChatGPT’s introduction—a potent AI chatbot built on LLMs being a noteworthy milestone received a great deal of public interest. LLMs’ technical development has had a significant impact on AI community, which have fundamentally altered how we create and employ AI systems. Given this rapid advancement in technology, we evaluate current developments in LLMs in this survey by explaining the backdrop, major findings, and mainstream techniques. Pre-training, adaptation adjustment, use, and capacity evaluation—the four core LLM components—are the ones we focus on. We also discuss the difficulties that still need to be overcome in order to advance future advances, as well as the resources that are available for developing LLMs. For both academics and engineers, this study provides a current review of the LLM literature.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Guo, B., Zhang, X., Wang, Z., Jiang, M., Nie, J., Ding, Y., Jianwei, Y., & Yupeng, W. (2023). How close is ChatGPT to human experts? Comparison corpus, evaluation, and detection. arXiv:2301.07597v1 [cs.CL] Guo, B., Zhang, X., Wang, Z., Jiang, M., Nie, J., Ding, Y., Jianwei, Y., & Yupeng, W. (2023). How close is ChatGPT to human experts? Comparison corpus, evaluation, and detection. arXiv:​2301.​07597v1 [cs.CL]
2.
Zurück zum Zitat Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., Du, Y., Yang, C., Chen, Y., Chen, Z., Jiang, J., Ren, R., Li, Y., Tang, X., Liu, Z., & Wen, J. (2023). A survey of large language models. arXiv:2303.18223 [cs.CL] Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., Du, Y., Yang, C., Chen, Y., Chen, Z., Jiang, J., Ren, R., Li, Y., Tang, X., Liu, Z., & Wen, J. (2023). A survey of large language models. arXiv:​2303.​18223 [cs.CL]
3.
Zurück zum Zitat Kirchner, J. H., Ahmad, L., Aaronson, S., & Leike, J. (2023). New AI classifier for indicating AI-written text. OpenAI. Kirchner, J. H., Ahmad, L., Aaronson, S., & Leike, J. (2023). New AI classifier for indicating AI-written text. OpenAI.
4.
Zurück zum Zitat Kamruzzaman, S. M., & Haider, F. (2010). A hybrid learning algorithm for text classification. arXiv preprint arXiv:1009.4574 Kamruzzaman, S. M., & Haider, F. (2010). A hybrid learning algorithm for text classification. arXiv preprint arXiv:​1009.​4574
5.
Zurück zum Zitat Liyanage, V., Buscaldi, D., & Nazarenko, A. (2022, April 29). A benchmark corpus for the detection of automatically generated text in academic publications. arXiv:2022.02013v2 [cs.CL] Liyanage, V., Buscaldi, D., & Nazarenko, A. (2022, April 29). A benchmark corpus for the detection of automatically generated text in academic publications. arXiv:2022.02013v2 [cs.CL]
6.
Zurück zum Zitat Jacovi, A., Shalom, O. S., & Goldberg, Y. (2018). Understanding convolutional neural networks for text classification. arXiv preprint arXiv:1809.08037 Jacovi, A., Shalom, O. S., & Goldberg, Y. (2018). Understanding convolutional neural networks for text classification. arXiv preprint arXiv:​1809.​08037
7.
Zurück zum Zitat Chen, J., Hu, Y., Liu, J., Xiao, Y., & Jiang, H. (2019). Deep short text classification with knowledge powered attention. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 33, No. 01, pp. 6252–6259). Chen, J., Hu, Y., Liu, J., Xiao, Y., & Jiang, H. (2019). Deep short text classification with knowledge powered attention. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 33, No. 01, pp. 6252–6259).
8.
Zurück zum Zitat Garg, S., & Ramakrishnan, G. (2020). Bae: Bert-based adversarial examples for text classification. arXiv preprint arXiv:2004.01970 Garg, S., & Ramakrishnan, G. (2020). Bae: Bert-based adversarial examples for text classification. arXiv preprint arXiv:​2004.​01970
9.
Zurück zum Zitat Zellers, R., Holtzman, A., Rashkin, H., Bisk, Y., Farhadi, A., Roesner, F., & Choi, Y. (2020, December). Defending against neural fake news. arXiv:1905.12616v3 [cs.CL] Zellers, R., Holtzman, A., Rashkin, H., Bisk, Y., Farhadi, A., Roesner, F., & Choi, Y. (2020, December). Defending against neural fake news. arXiv:​1905.​12616v3 [cs.CL]
10.
Zurück zum Zitat Kobis, N., & Mossink, L. D. (2020, December). Artificial intelligence versus Maya Angelou: Experimental evidence that people cannot differentiate AI-generated from human-written poetry. Elsevier. Kobis, N., & Mossink, L. D. (2020, December). Artificial intelligence versus Maya Angelou: Experimental evidence that people cannot differentiate AI-generated from human-written poetry. Elsevier.
11.
Zurück zum Zitat Kushnareva, L., Cherniavskii, D., Mikhailov, V., Artemova, E., Barannikov, S., Bernstein, A., Piontkovskaya, I., Piontkovski, D., & Burnaev, E. (2021, September). Artificial text detection via examining the topology of attention maps. arXiv:2109.04825 Kushnareva, L., Cherniavskii, D., Mikhailov, V., Artemova, E., Barannikov, S., Bernstein, A., Piontkovskaya, I., Piontkovski, D., & Burnaev, E. (2021, September). Artificial text detection via examining the topology of attention maps. arXiv:2109.04825
12.
Zurück zum Zitat Xie, Z., Brophy, J., Noack, A., You, W., Asthana, K., Perkins, C., Reis, S., Singh, S., & Lowd, D. (2022). Identifying adversarial attacks on text classifiers. arXiv:2204.03848 Xie, Z., Brophy, J., Noack, A., You, W., Asthana, K., Perkins, C., Reis, S., Singh, S., & Lowd, D. (2022). Identifying adversarial attacks on text classifiers. arXiv:​2204.​03848
13.
Zurück zum Zitat Maa, Y., Jiawei, L., Yi, F., Cheng, Q., Huang, Y., Lu, W., & Liu, X. (2023, January). Is this abstract generated by AI? A research for the gap between AI-generated scientific text and human-written scientific T. Research Gate. Maa, Y., Jiawei, L., Yi, F., Cheng, Q., Huang, Y., Lu, W., & Liu, X. (2023, January). Is this abstract generated by AI? A research for the gap between AI-generated scientific text and human-written scientific T. Research Gate.
14.
Zurück zum Zitat Woo, D. J., Susanto, H., Yeung, C. H., Guo, K., & Fung, A. K. Y. (2023, March). Exploring AI-generated text in student writing: How does AI help? Research Gate. Woo, D. J., Susanto, H., Yeung, C. H., Guo, K., & Fung, A. K. Y. (2023, March). Exploring AI-generated text in student writing: How does AI help? Research Gate.
15.
Zurück zum Zitat Kutela, B., Msechu, K., Das, S., & Kidando, E. (2023, January 19). Chatgpt’s scientific writings: A case study on traffic safety. Available at SSRN. Kutela, B., Msechu, K., Das, S., & Kidando, E. (2023, January 19). Chatgpt’s scientific writings: A case study on traffic safety. Available at SSRN.
16.
Zurück zum Zitat Sadasivan, V. S., Kumar, A., Balasubramanian, S., Wang, W., Feizi, S. (2023, March). Can AI-generated text be reliably detected? arXiv:2303.11156 [cs.CL] Sadasivan, V. S., Kumar, A., Balasubramanian, S., Wang, W., Feizi, S. (2023, March). Can AI-generated text be reliably detected? arXiv:​2303.​11156 [cs.CL]
17.
Zurück zum Zitat Mitrovi, S., Andreoletti, D., & Ayoub, O. (2023). ChatGPT or human? Detect and explain. Explaining decisions of machine learning model for detecting short chat GPT-generated text. arXiv:2301.13852v1 [cs.CL] Mitrovi, S., Andreoletti, D., & Ayoub, O. (2023). ChatGPT or human? Detect and explain. Explaining decisions of machine learning model for detecting short chat GPT-generated text. arXiv:​2301.​13852v1 [cs.CL]
18.
Zurück zum Zitat Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. arXiv:1706.03762 Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. arXiv:​1706.​03762
19.
Zurück zum Zitat Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A robustly optimized BERT pretraining approach. arXiv:1907.11692 Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A robustly optimized BERT pretraining approach. arXiv:​1907.​11692
20.
Zurück zum Zitat Fan, L., Li, L., Ma, Z., Lee, S., Yu, H., & Hemphill, L. (2023). A bibliometric review of large language models research from 2017 to 2023. arXiv:2304.02020 Fan, L., Li, L., Ma, Z., Lee, S., Yu, H., & Hemphill, L. (2023). A bibliometric review of large language models research from 2017 to 2023. arXiv:​2304.​02020
Metadaten
Titel
A Systematic Analysis of Diverse Large Language Models and Their Operational Paradigm
verfasst von
Omkar Bhattarai
Raj Chaudhary
Rahul Kumar
Ali Imam Abidi
Copyright-Jahr
2025
Verlag
Springer Nature Singapore
DOI
https://doi.org/10.1007/978-981-97-4152-6_43