{"id":{"repo_id":"mtu","oai_identifier":"oai:digitalcommons.mtu.edu:etdr-2899"},"canonical_url":"https://search.ndltd.org/etd/mtu/oai:digitalcommons.mtu.edu:etdr-2899","repository":{"repo_id":"mtu","name":"Michigan Technological University","base_url":"https://digitalcommons.mtu.edu/do/oai/"},"display":{"title":"ADVANCING HEALTH LITERACY THROUGH GENERATIVE AI: THE UTILIZATION OF OPEN-SOURCE LARGE LANGUAGE MODELS (LLMS) FOR TEXT SIMPLIFICATION AND READABILITY","abstract":"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.","abstract_html":"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.","abstract_has_math":false,"creators":["Sifat Naseem,"],"institution":null,"degree_name":"Master of Science in Health Informatics (MS)","degree_level":"Campus Access Master's Thesis","degree_discipline":"Department of Applied Computing","degree_department":null,"school":null,"contributors":["Guy Hembroff"],"advisors":[],"committee_chairs":[],"committee_members":["Rongua Xu","Paniz Hazaveh"],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:19:03Z","subjects":["LLMs","Text simplification","Llama-2","Health Literacy","Flesch Kincaid grade scale","Fine-tuning"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.mtu.edu/etdr/1762"],"render_values":[{"text":"https://digitalcommons.mtu.edu/etdr/1762","href":"https://digitalcommons.mtu.edu/etdr/1762","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.37099/mtu.dc.etdr/1762","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/10.37099/mtu.dc.etdr/1762","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.mtu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.mtu.edu%3Aetdr-2899","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Guy Hembroff"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Rongua Xu","Paniz Hazaveh"]},{"key":"dc:creator","label":"Author","values":["Sifat Naseem,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.created","label":"Dc Date Created","values":["2024-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Department of Applied Computing"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Campus Access Master's Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Health Informatics (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["LLMs","Text simplification","Llama-2","Health Literacy","Flesch Kincaid grade scale","Fine-tuning"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["10.37099/mtu.dc.etdr/1762","https://digitalcommons.mtu.edu/etdr/1762"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:title","label":"Title","values":["ADVANCING HEALTH LITERACY THROUGH GENERATIVE AI: THE UTILIZATION OF OPEN-SOURCE LARGE LANGUAGE MODELS (LLMS) FOR TEXT SIMPLIFICATION AND READABILITY"]}]}],"canonical_facts":{"dc:contributor":["Guy Hembroff"],"dc:contributor.committeemember":["Rongua Xu","Paniz Hazaveh"],"dc:creator":["Sifat Naseem,"],"dc:date.created":["2024-01-01T08:00:00Z"],"dc:description.abstract":["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."],"dc:identifier":["10.37099/mtu.dc.etdr/1762","https://digitalcommons.mtu.edu/etdr/1762"],"dc:subject":["LLMs","Text simplification","Llama-2","Health Literacy","Flesch Kincaid grade scale","Fine-tuning"],"dc:title":["ADVANCING HEALTH LITERACY THROUGH GENERATIVE AI: THE UTILIZATION OF OPEN-SOURCE LARGE LANGUAGE MODELS (LLMS) FOR TEXT SIMPLIFICATION AND READABILITY"],"thesis:degree_discipline":["Department of Applied Computing"],"thesis:degree_level":["Campus Access Master's Thesis"],"thesis:degree_name":["Master of Science in Health Informatics (MS)"]},"updated_at":"2026-11-19T08:19:03Z"}