Version 1
: Received: 13 May 2023 / Approved: 15 May 2023 / Online: 15 May 2023 (12:53:11 CEST)
How to cite:
Tasar, D.E.; Öcal Taşar, C. Bridging History with AI: A Comparative Evaluation of GPT- 3.5, GPT-4, and Google-BARD in Predictive Accuracy and Fact- Checking. Preprints2023, 2023051047. https://doi.org/10.20944/preprints202305.1047.v1
Tasar, D.E.; Öcal Taşar, C. Bridging History with AI: A Comparative Evaluation of GPT- 3.5, GPT-4, and Google-BARD in Predictive Accuracy and Fact- Checking. Preprints 2023, 2023051047. https://doi.org/10.20944/preprints202305.1047.v1
Tasar, D.E.; Öcal Taşar, C. Bridging History with AI: A Comparative Evaluation of GPT- 3.5, GPT-4, and Google-BARD in Predictive Accuracy and Fact- Checking. Preprints2023, 2023051047. https://doi.org/10.20944/preprints202305.1047.v1
APA Style
Tasar, D.E., & Öcal Taşar, C. (2023). Bridging History with AI: A Comparative Evaluation of GPT- 3.5, GPT-4, and Google-BARD in Predictive Accuracy and Fact- Checking. Preprints. https://doi.org/10.20944/preprints202305.1047.v1
Chicago/Turabian Style
Tasar, D.E. and Ceren Öcal Taşar. 2023 "Bridging History with AI: A Comparative Evaluation of GPT- 3.5, GPT-4, and Google-BARD in Predictive Accuracy and Fact- Checking" Preprints. https://doi.org/10.20944/preprints202305.1047.v1
Abstract
The rapid proliferation of information in the digital era underscores the importance of accurate historical representation and interpretation. While artificial intelligence (AI) has shown promise in various fields, its potential for historical fact-checking and gap-filling remains largely untapped. This study evaluates the performance of three large language models (LLMs)—GPT-3.5, GPT-4, and Google- BARD—in the context of predicting and verifying historical events based on given data. A novel metric, "Distance to Reality" (DTR), is introduced to assess the models' outputs against established historical facts. The results reveal a substantial potential for AI in historical studies, with GPT-4 demonstrating superior performance. This paper underscores the need for further research into AI's role in enriching our understanding of the past and bridging historical knowledge gaps.
Keywords
Artificial Intelligence; Large Language Models; GPT-3.5; GPT-4; Google-BARD; Historical Fact-Checking; Distance to Reality; History; AI in Education; Gap Bridging
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
