Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4

In this study, we investigate the role of Generative Pre-trained Transformer 4 (GPT-4) in enhancing interpretability of sequential predictions in Natural Language Processing (NLP). Our study introduces a hybrid model that integrates traditional sequential prediction models with GPT-4, aiming to gene...

Full description

Saved in:
Bibliographic Details
Main Author: Mohammed Rasol Al Saidat (author)
Other Authors: Khaled Shaalan (author), Suliman Yemria (author)
Published: 2025
Online Access:https://bspace.buid.ac.ae/handle/1234/3166
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1862980611216506880
author Mohammed Rasol Al Saidat
author2 Khaled Shaalan
Suliman Yemria
author2_role author
author
author_facet Mohammed Rasol Al Saidat
Khaled Shaalan
Suliman Yemria
author_role author
dc.creator.none.fl_str_mv Mohammed Rasol Al Saidat
Khaled Shaalan
Suliman Yemria
dc.date.none.fl_str_mv 2025-05-31T13:42:34Z
2025-05-31T13:42:34Z
2025
dc.identifier.none.fl_str_mv Al Saidat, M.R., Shaalan, K., Yemria, S. (2025). Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4. In: Al Marri, K., Mir, F.A., Awad, A., Abubakar, A. (eds) BUiD Doctoral Research Conference 2024. BDRC 2024. Lecture Notes in Civil Engineering, vol 587. Springer, Cham. https://doi.org/10.1007/978-3-031-84371-6_3
HB: 9783031843709 eBook: 9783031843716
https://bspace.buid.ac.ae/handle/1234/3166
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv Springer Cham
dc.relation.none.fl_str_mv Lecture Notes in Civil Engineering; 587
dc.title.none.fl_str_mv Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4
dc.type.none.fl_str_mv Book chapter
description In this study, we investigate the role of Generative Pre-trained Transformer 4 (GPT-4) in enhancing interpretability of sequential predictions in Natural Language Processing (NLP). Our study introduces a hybrid model that integrates traditional sequential prediction models with GPT-4, aiming to generate detailed, context-sensitive explanations for model outputs. This approach is rooted in the use of advanced transformer architectures and a specialized tokenization method that maintains semantic coherence, allowing for deep contextual analysis by GPT-4. Additionally, we devise a rationale generation algorithm that achieves a balance between succinctness and informativeness. Our experimental validation spans across various high-dimensional datasets, including financial time-series and multilingual texts, employing both qualitative and quantitative metrics to evaluate the model’s performance. These metrics focus on the plausibility and consistency of the rationales, as well as the model’s predictive accuracy. Preliminary results demonstrate that our approach not only enhances the accuracy of sequential predictions but also significantly improves their interpretability. This finding highlights the potential of generative AI to bridge the gap between complex AI decision-making processes. This research underscores the viability of employing generative AI to elucidate the underlying mechanisms of sequential prediction models, paving the way for more transparent AI systems.
id budr_3eed88877cf1774d2a9f4b44edc946ea
identifier_str_mv Al Saidat, M.R., Shaalan, K., Yemria, S. (2025). Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4. In: Al Marri, K., Mir, F.A., Awad, A., Abubakar, A. (eds) BUiD Doctoral Research Conference 2024. BDRC 2024. Lecture Notes in Civil Engineering, vol 587. Springer, Cham. https://doi.org/10.1007/978-3-031-84371-6_3
HB: 9783031843709 eBook: 9783031843716
language_invalid_str_mv en
network_acronym_str budr
network_name_str The British University in Dubai repository
oai_identifier_str oai:bspace.buid.ac.ae:1234/3166
publishDate 2025
publisher.none.fl_str_mv Springer Cham
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4Mohammed Rasol Al SaidatKhaled ShaalanSuliman YemriaIn this study, we investigate the role of Generative Pre-trained Transformer 4 (GPT-4) in enhancing interpretability of sequential predictions in Natural Language Processing (NLP). Our study introduces a hybrid model that integrates traditional sequential prediction models with GPT-4, aiming to generate detailed, context-sensitive explanations for model outputs. This approach is rooted in the use of advanced transformer architectures and a specialized tokenization method that maintains semantic coherence, allowing for deep contextual analysis by GPT-4. Additionally, we devise a rationale generation algorithm that achieves a balance between succinctness and informativeness. Our experimental validation spans across various high-dimensional datasets, including financial time-series and multilingual texts, employing both qualitative and quantitative metrics to evaluate the model’s performance. These metrics focus on the plausibility and consistency of the rationales, as well as the model’s predictive accuracy. Preliminary results demonstrate that our approach not only enhances the accuracy of sequential predictions but also significantly improves their interpretability. This finding highlights the potential of generative AI to bridge the gap between complex AI decision-making processes. This research underscores the viability of employing generative AI to elucidate the underlying mechanisms of sequential prediction models, paving the way for more transparent AI systems.Springer Cham2025-05-31T13:42:34Z2025-05-31T13:42:34Z2025Book chapterAl Saidat, M.R., Shaalan, K., Yemria, S. (2025). Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4. In: Al Marri, K., Mir, F.A., Awad, A., Abubakar, A. (eds) BUiD Doctoral Research Conference 2024. BDRC 2024. Lecture Notes in Civil Engineering, vol 587. Springer, Cham. https://doi.org/10.1007/978-3-031-84371-6_3HB: 9783031843709 eBook: 9783031843716https://bspace.buid.ac.ae/handle/1234/3166enLecture Notes in Civil Engineering; 587oai:bspace.buid.ac.ae:1234/31662025-05-31T13:42:34Z
spellingShingle Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4
Mohammed Rasol Al Saidat
title Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4
title_full Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4
title_fullStr Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4
title_full_unstemmed Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4
title_short Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4
title_sort Advancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4
url https://bspace.buid.ac.ae/handle/1234/3166