Off-campus Michigan Tech users: To download campus access theses or dissertations, please use the following button to log in with your Michigan Tech ID and password: log in to proxy server

Non-Michigan Tech users: Please talk to your librarian about requesting this thesis or dissertation through interlibrary loan.

Date of Award


Document Type

Campus Access Master's Thesis

Degree Name

Master of Science in Health Informatics (MS)

Administrative Home Department

Department of Applied Computing

Advisor 1

Guy Hembroff

Committee Member 1

Rongua Xu

Committee Member 2

Paniz Hazaveh


As the world is shifting towards digital platforms, it is important to make sure that available online information is accessible and comprehensible to audiences with limited literacy levels. The widespread use of LLMs makes it important to access their responses for simplification tasks especially when they are used for healthcare purposes to make sure that generated information is understandable to people with low literacy. In this research, responses generated by LLMs such as ChatGPT and Llama-2 are evaluated for simplification tasks using the Flesch Kincaid Grade scale. Instruction tuning is performed to evaluate the generation of simplified responses by LLMs according to reading grade level. Fine-tuning of Llama-2-7-B on a dataset containing the correct formula of the Flesch Kincaid grade scale is done using SFTTrainer. To maintain overall robustness, the fine-tuned model is merged with the base model, and evaluation is conducted. A calculator function is used for calculating the Flesch Kincaid reading grade level formula given the user input to guide the model for response text generation respective to the user’s grade level of understanding. Our research focused on the refinement of text simplification methodologies, warranting the response generated by LLMs, particularly related to healthcare, to become accessible and understandable to individuals as per their literacy levels.