{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-4827"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-4827","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Building a Novel Question-Answering System using Retrieval-Augmented Generation for the California Fair Political Practices Commission","abstract":"The California Fair Political Practices Commission (FPPC) receives a high volume of inquiries via email from public officials, the general public, and other agencies, which currently requires staff to manually search through informational documents and manuals to provide timely responses. This process is both labor- and time-intensive. To address this challenge, we design a question-answering (QA) system that drafts responses to emailed questions by retrieving relevant information from the FPPC’s manuals using a retrieval-augmented generation (RAG) framework. Although the current implementation focuses on a single manual, the system is designed to be adaptable to the broader set of FPPC documents. By converting the FPPC’s pub- licly available PDF manuals into Markdown files, we parse and segment text into sec- tions, retrieve documentation relevant to a query, and utilize a large language model (OpenAI’s ChatGPT-4.1) to generate responses grounded in the retrieved text. Our hypothesis is that a RAG-based QA system with custom document parsing for information retrieval performs better, i.e. gives more accurate and correct answers grounded within the source data, than direct application of state-of-the-art LLMs like ChatGPT. We validate our approach through manual review of retrieval accuracy and generated answers, as well as through a survey on Prolific, where participants compare responses from our system against those generated by directly querying ChatGPT with the FPPC manual.","abstract_html":"The California Fair Political Practices Commission (FPPC) receives a high volume of inquiries via email from public officials, the general public, and other agencies, which currently requires staff to manually search through informational documents and manuals to provide timely responses. This process is both labor- and time-intensive. To address this challenge, we design a question-answering (QA) system that drafts responses to emailed questions by retrieving relevant information from the FPPC’s manuals using a retrieval-augmented generation (RAG) framework. Although the current implementation focuses on a single manual, the system is designed to be adaptable to the broader set of FPPC documents. By converting the FPPC’s pub- licly available PDF manuals into Markdown files, we parse and segment text into sec- tions, retrieve documentation relevant to a query, and utilize a large language model (OpenAI’s ChatGPT-4.1) to generate responses grounded in the retrieved text. Our hypothesis is that a RAG-based QA system with custom document parsing for information retrieval performs better, i.e. gives more accurate and correct answers grounded within the source data, than direct application of state-of-the-art LLMs like ChatGPT. We validate our approach through manual review of retrieval accuracy and generated answers, as well as through a survey on Prolific, where participants compare responses from our system against those generated by directly querying ChatGPT with the FPPC manual.","abstract_has_math":false,"creators":["Dua, Saanvi"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Foaad Khosmood","Computer Science","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:41Z","subjects":["FPPC","Retrieval Augmented Generation","QA system","NLP","Question Answering","Artificial Intelligence and Robotics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/3158","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/3158","record_label":"Repository record","record_kind":"record","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.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-4827","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Foaad Khosmood","Computer Science","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Dua, Saanvi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-09-05T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2025-09-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["FPPC","Retrieval Augmented Generation","QA system","NLP","Question Answering","Artificial Intelligence and Robotics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/3158"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The California Fair Political Practices Commission (FPPC) receives a high volume of inquiries via email from public officials, the general public, and other agencies, which currently requires staff to manually search through informational documents and manuals to provide timely responses. This process is both labor- and time-intensive. To address this challenge, we design a question-answering (QA) system that drafts responses to emailed questions by retrieving relevant information from the FPPC’s manuals using a retrieval-augmented generation (RAG) framework. Although the current implementation focuses on a single manual, the system is designed to be adaptable to the broader set of FPPC documents. By converting the FPPC’s pub- licly available PDF manuals into Markdown files, we parse and segment text into sec- tions, retrieve documentation relevant to a query, and utilize a large language model (OpenAI’s ChatGPT-4.1) to generate responses grounded in the retrieved text. Our hypothesis is that a RAG-based QA system with custom document parsing for information retrieval performs better, i.e. gives more accurate and correct answers grounded within the source data, than direct application of state-of-the-art LLMs like ChatGPT. We validate our approach through manual review of retrieval accuracy and generated answers, as well as through a survey on Prolific, where participants compare responses from our system against those generated by directly querying ChatGPT with the FPPC manual."]},{"key":"dc:title","label":"Title","values":["Building a Novel Question-Answering System using Retrieval-Augmented Generation for the California Fair Political Practices Commission"]}]}],"canonical_facts":{"dc:contributor":["Foaad Khosmood","Computer Science","College of Engineering"],"dc:creator":["Dua, Saanvi"],"dc:date.available":["2025-09-05T07:00:00Z"],"dc:date.created":["2025-09-01T07:00:00Z"],"dc:description.abstract":["The California Fair Political Practices Commission (FPPC) receives a high volume of inquiries via email from public officials, the general public, and other agencies, which currently requires staff to manually search through informational documents and manuals to provide timely responses. This process is both labor- and time-intensive. To address this challenge, we design a question-answering (QA) system that drafts responses to emailed questions by retrieving relevant information from the FPPC’s manuals using a retrieval-augmented generation (RAG) framework. Although the current implementation focuses on a single manual, the system is designed to be adaptable to the broader set of FPPC documents. By converting the FPPC’s pub- licly available PDF manuals into Markdown files, we parse and segment text into sec- tions, retrieve documentation relevant to a query, and utilize a large language model (OpenAI’s ChatGPT-4.1) to generate responses grounded in the retrieved text. Our hypothesis is that a RAG-based QA system with custom document parsing for information retrieval performs better, i.e. gives more accurate and correct answers grounded within the source data, than direct application of state-of-the-art LLMs like ChatGPT. We validate our approach through manual review of retrieval accuracy and generated answers, as well as through a survey on Prolific, where participants compare responses from our system against those generated by directly querying ChatGPT with the FPPC manual."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/3158"],"dc:subject":["FPPC","Retrieval Augmented Generation","QA system","NLP","Question Answering","Artificial Intelligence and Robotics"],"dc:title":["Building a Novel Question-Answering System using Retrieval-Augmented Generation for the California Fair Political Practices Commission"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-11-19T07:12:41Z"}