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

Simple item page
dc.contributor.authorMohammed Rasol Al Saidat
dc.contributor.authorKhaled Shaalan
dc.contributor.authorSuliman Yemria
dc.date.accessioned2025-05-31T13:42:34Z
dc.date.available2025-05-31T13:42:34Z
dc.date.issued2025
dc.description.abstractIn 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.
dc.identifier.citationAl 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
dc.identifier.isbnHB: 9783031843709 eBook: 9783031843716
dc.identifier.urihttps://bspace.buid.ac.ae/handle/1234/3166
dc.language.isoen
dc.publisherSpringer Cham
dc.relation.ispartofseriesLecture Notes in Civil Engineering; 587
dc.titleAdvancing Interpretability in Sequential Models Through Generative AI Rationalization Using GPT-4
dc.typeBook chapter
Files
License bundle
Now showing 1 - 1 of 1
Name:
license.txt
Size:
1.35 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
BUiD Doctoral Research Conference 2024