University of Twente Student Theses
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.
Prompt Engineering : Addressing Socioeconomic Bias in LLM-Based Insurance Prescreening
Tulbure, Mihai (2025) Prompt Engineering : Addressing Socioeconomic Bias in LLM-Based Insurance Prescreening.
|
PDF
1MB |
| Abstract: | Large Language Models (LLMs) are a type of artificial intelligence (AI) that is able to manipulate, generate and understand human language in multiple applications such as tech and banking. Despite their exponential capabilities, bias can still be present, specifically the socioeconomic bias. However, it is still difficult to assess full transparency due to the complexity of the model, such as ChatGPT. An empirical study is conducted to explore ChatGPT outputs during the prescreening of insurance applications. This research contributes to the scientific understanding of how prompt engineering can be utilized to mitigate socioeconomic bias and prevent discriminatory outcomes in financial services. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Business & IT BSc (56066) |
| Link to this item: | https://purl.utwente.nl/essays/107626 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page