Authors : Avikal Chauhan; CH Pawan; C Vishwash; Aditya Dillon; Bharani Kumar Depuru

Volume/Issue : Volume 9 - 2024, Issue 12 - December

Google Scholar : https://tinyurl.com/a8xdzp2r

DOI : https://doi.org/10.38124/ijisrt/24dec299

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The swift progress of large language models [1] in recent times has profoundly influenced the trajectory of natural language processing. This evolution has been propelled by exponential growth in computational resources, the increasing availability of expansive data, and refinements in algorithmic methodologies. Transitioning from the rudimentary rule- based frameworks to today’s complex architectures, LLMs have undergone substantial transformation. Early models showcased the capacity for generating coherent and contextually applicable content but recent enhancements have significantly augmented both comprehension and content generation capabilities marking a pivotal leap in language model sophistication. The expansion of open-source LLMs [2] has transformed the sphere of advanced linguistic innovations, contributing unprecedented access for experimentation and implementation across sectors, such as education recent breakthroughs in prompt enhancing have redefined how these models are harnessed, producing very accurate contextually aware outputs without requiring exhaustive retraining processes. Within the educational domain, large language models LLMs present a paradigm shift by streamlining text automation significantly mitigating the laborious, and resource-heavy demands of traditional manual tasks. This advancement empowers educators to devote more attention to pedagogy and direct student interaction. On top of that, the fusion of sophisticated LLMs accompanied by optimized prompting strategies [3] in scholastic platforms elevates the educational experience, delivering tailored high-caliber, and contextually pertinent material. This approach fosters a more adaptive and systematic learning ecosystem enhancing the overall instructional framework.

Keywords : AI-Enhanced Content Generation, Large Language Models, RAG, Prompt Techniques, Q&A-Summary system, Lang Chain Framework, Plagiarism.

References :

1. Kamath, U., Keenan, K., Somers, G., Sorenson, S. (2024). LLMs: Evolution and New Frontiers. In: Large Language Models: A Deep Dive. Springer, Cham. https://doi.org/10.1007/978-3-031-65647-7_10
2. Sanjay Kukreja, Tarun Kumar, Amit Purohit, Abhijit Dasgupta, and Debashis Guha. 2024. A Literature Survey on Open Source Large Language Models. In Proceedings of the 2024 7th International Conference on Computers in Management and Business (ICCMB '24). Association for Computing Machinery, New York, NY, USA, 133–143. https://doi.org/10.1145/3647782.3647803
3. Marvin, G., Hellen, N., Jjingo, D., Nakatumba-Nabende, J. (2024). Prompt Engineering in Large Language Models. In: Jacob, I.J., Piramuthu, S., Falkowski-Gilski, P. (eds) Data Intelligence and Cognitive Informatics. ICDICI 2023. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-99-7962-2_30
4. Gemini’s big upgrade: Faster responses with 1.5 Flash, expanded access and more. https://blog.google/products/gemini/google-gemini-new-features-july-2024/
5. Mihalcea, R., Liu, H., Lieberman, H. (2006). NLP (Natural Language Processing) for NLP (Natural Language Programming). In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2006. Lecture Notes in Computer Science, vol 3878. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11671299_34
6. Leo S. Lo, The CLEAR path: A framework for enhancing information literacy through prompt engineering,The Journal of Academic Librarianship, Volume 49, Issue 4, 2023, 102720, ISSN 0099-1333, https://doi.org/10.1016/j.acalib.2023.102720
7. Studer, S.; Bui, T.B.; Drescher, C.; Hanuschkin, A.; Winkler, L.; Peters, S.; Müller, K.-R. Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology. Mach. Learn. Knowl. Extr. 2021, 3, 392-413. https://doi.org/10.3390/make3020020
8. Jing Li, Peizhang Wang, Lu Jia, Run Mao, Qian Li, Yongle He, Yi Sun, Pinwang Zhao Design and implementation of an automated PDF drawing statistics tool based on Python. Proceedings Volume 12800, Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023); 128006R (2023) https://doi.org/10.1117/12.3003927
9. Bhaskarjit Sarmah, Dhagash Mehta, Stefano Pasquali, and Tianjie Zhu. 2024. Towards reducing hallucination in extracting information from financial reports using Large Language Models. In Proceedings of the Third International Conference on AI-ML Systems (AIMLSystems '23). Association for Computing Machinery, New York, NY, USA, Article 39, 1–5. https://doi.org/10.1145/3639856.3639895
10. [10] Selva Birunda, S., Kanniga Devi, R. (2021). A Review on Word Embedding Techniques for Text Classification. In: Raj, J.S., Iliyasu, A.M., Bestak, R., Baig, Z.A. (eds) Innovative Data Communication Technologies and Application. Lecture Notes on Data Engineering and Communications Technologies, vol 59. Springer, Singapore. https://doi.org/10.1007/978-981-15-9651-3_23
11. A. Singh, A. Ehtesham, S. Mahmud and J. -H. Kim, "Revolutionizing Mental Health Care through LangChain: A Journey with a Large Language Model," 2024 IEEE 14th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA, 2024, pp. 0073-0078, https://doi.org/10.1109/CCWC60891.2024.10427865
12. Aman Madaan, Katherine Hermann, and Amir Yazdanbakhsh. 2023. What Makes Chain-of-Thought Prompting Effective? A Counterfactual Study. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1448–1535, Singapore. Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.findings-emnlp.101
13. T. Ahmed and P. Devanbu, "Better Patching Using LLM Prompting, via Self-Consistency," 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE), Luxembourg, Luxembourg, 2023, pp. 1742-1746, https://doi.org/10.1109/ASE56229.2023.00065
14. Diao, S., Wang, P., Lin, Y., Pan, R., Liu, X., & Zhang, T. (2023). Active Prompting with Chain-of-Thought for Large Language Models. [Submitted on 23 Feb 2023 (v1), last revised 21 Jul 2024 (this version, v5)] ArXiv. /abs/2302.12246 https://doi.org/10.48550/arXiv.2302.12246
15. Mondillo, G., Frattolillo, V., Colosimo, S. et al. Basal knowledge in the field of pediatric nephrology and its enhancement following specific training of ChatGPT-4 “omni” and Gemini 1.5 Flash. Pediatr Nephrol (2024). https://doi.org/10.1007/s00467-024-06486-3
16. Multimodality with Gemini-1.5-Flash: Technical Details and Use Cases https://medium.com/google-cloud/multimodality-with-gemini-1-5-flash-technical-details-and-use-cases-84e8440625b6

17. Pengshan Cai, Zonghai Yao, Fei Liu, Dakuo Wang, Meghan Reilly, Huixue Zhou, Lingxi Li, Yi Cao, Alok Kapoor, Adarsha Bajracharya, Dan Berlowitz, Hong Yu; PaniniQA: Enhancing Patient Education Through Interactive Question Answering. Transactions of the Association for Computational Linguistics 2023; 11 1518–1536. https://doi.org/10.1162/tacl_a_00616