Bridging History with AI A Comparative Evaluation of GPT 3.5, GPT4, and GoogleBARD in Predictive Accuracy and Fact Checking
This addresses the problem of historical fact-checking and gap-filling for historians and researchers, though it appears incremental as it compares existing models on a new application.
This study evaluated GPT-3.5, GPT-4, and GoogleBARD for predicting and verifying historical events, introducing a novel 'Distance to Reality' metric. GPT-4 demonstrated superior performance, showing substantial potential for AI in historical studies.
The rapid proliferation of information in the digital era underscores the importance of accurate historical representation and interpretation. While artificial intelligence 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 GoogleBARD 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.