AHCI RESEARCH GROUP
Publications
Papers published in international journals,
proceedings of conferences, workshops and books.
OUR RESEARCH
Scientific Publications
How to
Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
2024
Karabiyik, M. A.; Tan, F. G.; Yüksel, A. S.
Application of Prompt Engineering Techniques to Optimize Information Retrieval in the Metaverse Journal Article
In: Journal of Metaverse, vol. 4, no. 2, pp. 157–164, 2024, ISSN: 27920232 (ISSN).
Abstract | Links | BibTeX | Tags: Information Retrieval, large language models, Metaverse, Prompt engineering, response generation
@article{karabiyik_application_2024,
title = {Application of Prompt Engineering Techniques to Optimize Information Retrieval in the Metaverse},
author = {M. A. Karabiyik and F. G. Tan and A. S. Yüksel},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85214488898&doi=10.57019%2fjmv.1543077&partnerID=40&md5=2002b9db05ed3d57224828b384438785},
doi = {10.57019/jmv.1543077},
issn = {27920232 (ISSN)},
year = {2024},
date = {2024-01-01},
journal = {Journal of Metaverse},
volume = {4},
number = {2},
pages = {157–164},
abstract = {Prompt engineering techniques are instructions that enable large language models (LLMs) to solve real-world problems more effectively. These techniques enhance the capabilities of LLMs to generate accurate and efficient responses. Our study examines the challenge of acquiring comprehensive and efficient information in the metaverse through the application of various prompt engineering techniques. The main objective is to improve the accuracy and effectiveness of metaverse-related responses by leveraging LLM capabilities. In this study, 100 questions were generated using GPT, GEMINI, QWEN, and MISTRAL language models focusing on the metaverse. Our experiments indicated that responses often included unrelated information, highlighting the need for prompt engineering techniques. We applied knowledge-based, rule-based, few-shot, and template-based prompt engineering techniques to refine the responses. The performance of GPT, GEMINI, QWEN, and MISTRAL models were evaluated based on criteria including accuracy, timeliness, comprehensiveness, and consistency. Our findings reveal that prompt engineering techniques significantly enhance the efficacy of LLMs in providing improved information retrieval and response generation, aiding users in efficiently acquiring information in complex environments like the metaverse. © 2024, Izmir Academy Association. All rights reserved.},
keywords = {Information Retrieval, large language models, Metaverse, Prompt engineering, response generation},
pubstate = {published},
tppubtype = {article}
}
Prompt engineering techniques are instructions that enable large language models (LLMs) to solve real-world problems more effectively. These techniques enhance the capabilities of LLMs to generate accurate and efficient responses. Our study examines the challenge of acquiring comprehensive and efficient information in the metaverse through the application of various prompt engineering techniques. The main objective is to improve the accuracy and effectiveness of metaverse-related responses by leveraging LLM capabilities. In this study, 100 questions were generated using GPT, GEMINI, QWEN, and MISTRAL language models focusing on the metaverse. Our experiments indicated that responses often included unrelated information, highlighting the need for prompt engineering techniques. We applied knowledge-based, rule-based, few-shot, and template-based prompt engineering techniques to refine the responses. The performance of GPT, GEMINI, QWEN, and MISTRAL models were evaluated based on criteria including accuracy, timeliness, comprehensiveness, and consistency. Our findings reveal that prompt engineering techniques significantly enhance the efficacy of LLMs in providing improved information retrieval and response generation, aiding users in efficiently acquiring information in complex environments like the metaverse. © 2024, Izmir Academy Association. All rights reserved.
2023
Gaikwad, T.; Kulkarni, A.
Smart Training Framework and Assessment Strategies Proceedings Article
In: IEEE Eng. Informatics, EI, Institute of Electrical and Electronics Engineers Inc., 2023, ISBN: 979-835033852-2 (ISBN).
Abstract | Links | BibTeX | Tags: AR training, Assessment strategies, Augmented Reality, Augmented reality training, Computational Linguistics, Edtech, Education computing, Education sectors, Engineering education, Language Model, Large language model, large language models, Prompt engineering, Risk assessment, Smart assessment, Students, Training assessment, Training framework
@inproceedings{gaikwad_smart_2023,
title = {Smart Training Framework and Assessment Strategies},
author = {T. Gaikwad and A. Kulkarni},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85193969838&doi=10.1109%2fIEEECONF58110.2023.10520594&partnerID=40&md5=c23eba992e455b09829dd03d25fe567e},
doi = {10.1109/IEEECONF58110.2023.10520594},
isbn = {979-835033852-2 (ISBN)},
year = {2023},
date = {2023-01-01},
booktitle = {IEEE Eng. Informatics, EI},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {The rapidly evolving landscape of technological advancements is significantly transforming the education sector. This integration of technology in the education sector has given rise to the edtech industry which is transforming as newer technologies are introduced. Training delivered to the learners, along with the assessment of the learners, are the fundamental components of the education sector. However, current methods of delivering training and assessing learners face numerous challenges, including skill shortage due to technology advancements, high costs, conducting complex training in high- risk environments. Similarly, assessment methods struggle with inflexible assessment strategies and limited personalized feedback to learners. Addressing these challenges in training and assessment, this study proposes a smart training and assessment framework (STAF) which leverages the benefits of augmented reality (AR) and artificial intelligence (AI) based large language models (LLMs) which stand out as a monumental leap in reshaping the training and assessment sector. As part of this study, an AR based training module was created and delivered to students. A survey was conducted of these students to gain insights about the adaptability of AR based trainings and potential to improve these trainings. It is concluded that along with AR in education, AI and LLMs with prompt engineering strategies should be integrated in the education domain for better interactivity and enhanced student performance. Currently, limited research is conducted on integration of LLMs in AR environments for the education sector and this paper provides an in-depth exploration of the immense potential of the applications of LLMs within the realm of training and assessment for improved learner performance. © 2023 IEEE.},
keywords = {AR training, Assessment strategies, Augmented Reality, Augmented reality training, Computational Linguistics, Edtech, Education computing, Education sectors, Engineering education, Language Model, Large language model, large language models, Prompt engineering, Risk assessment, Smart assessment, Students, Training assessment, Training framework},
pubstate = {published},
tppubtype = {inproceedings}
}
The rapidly evolving landscape of technological advancements is significantly transforming the education sector. This integration of technology in the education sector has given rise to the edtech industry which is transforming as newer technologies are introduced. Training delivered to the learners, along with the assessment of the learners, are the fundamental components of the education sector. However, current methods of delivering training and assessing learners face numerous challenges, including skill shortage due to technology advancements, high costs, conducting complex training in high- risk environments. Similarly, assessment methods struggle with inflexible assessment strategies and limited personalized feedback to learners. Addressing these challenges in training and assessment, this study proposes a smart training and assessment framework (STAF) which leverages the benefits of augmented reality (AR) and artificial intelligence (AI) based large language models (LLMs) which stand out as a monumental leap in reshaping the training and assessment sector. As part of this study, an AR based training module was created and delivered to students. A survey was conducted of these students to gain insights about the adaptability of AR based trainings and potential to improve these trainings. It is concluded that along with AR in education, AI and LLMs with prompt engineering strategies should be integrated in the education domain for better interactivity and enhanced student performance. Currently, limited research is conducted on integration of LLMs in AR environments for the education sector and this paper provides an in-depth exploration of the immense potential of the applications of LLMs within the realm of training and assessment for improved learner performance. © 2023 IEEE.