{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129236"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129236","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Enhancing the verifiability of large language model based medical question answering systems","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","abstract_has_math":false,"creators":["Wang, Xiao"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Zhang, Minjia"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05-02","date_published":"2025-05-02","updated_at":"2026-07-22T22:25:04Z","subjects":["Large Language Models","Retrieval-Augmented Generation","Trustworthy AI","Verifiability","Citation Generation","Biomedical Question Answering"],"languages":["en","eng"],"rights":["Copyright 2025 Xiao Wang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129236","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Zhang, Minjia"]},{"key":"dc:creator","label":"Author","values":["Wang, Xiao"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-05-02","2025-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Large Language Models","Retrieval-Augmented Generation","Trustworthy AI","Verifiability","Citation Generation","Biomedical Question Answering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Xiao Wang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129236"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","The student, Xiao Wang, accepted the attached license on 2025-05-01 at 18:33.","The student, Xiao Wang, submitted this Thesis for approval on 2025-05-01 at 18:33.","This Thesis was approved for publication on 2025-05-02 at 16:38.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21900 on 2025-10-19 at 18:09:39","Large language models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks. However, their tendency to generate fluent yet unverifiable statements poses a fundamental challenge for deployment in high-stakes domains such as medicine, law, and education. This thesis addresses the central question of \\textit{verifiability}: how can LLMs produce outputs that are not only accurate but also supported by transparent, checkable evidence? Focusing on the concrete case of medical question answering (QA), this work investigates citation generation as a mechanism for enhancing verifiability. Rather than adhering to a fixed pipeline, the thesis follows an iterative, design-driven approach to evaluate how system-level decisions—including the use of parametric versus non-parametric knowledge, retrieval-augmented generation (RAG), and fine-grained attribution strategies—affect the alignment between model-generated content and external sources. Based on these insights, a two-pass citation framework is proposed. The approach first encourages in-context citation generation during answer formulation, followed by a post hoc retrieval and reranking stage that refines attribution at the statement level. This pipeline improves citation recall and precision while maintaining fluency and factual correctness. Additionally, a human annotation study reveals that recent general-purpose LLMs can serve as effective automatic judges of citation quality, often outperforming domain-specific NLI models in aligning with expert judgments. In summary, this thesis contributes both practical methods and conceptual frameworks for improving LLM verifiability in biomedical QA, with broader implications for developing trustworthy, evidence-supported AI in other knowledge-intensive fields."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Enhancing the verifiability of large language model based medical question answering systems"]}]}],"canonical_facts":{"dc:contributor":["Zhang, Minjia"],"dc:creator":["Wang, Xiao"],"dc:date":["2025-05-02","2025-05"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","The student, Xiao Wang, accepted the attached license on 2025-05-01 at 18:33.","The student, Xiao Wang, submitted this Thesis for approval on 2025-05-01 at 18:33.","This Thesis was approved for publication on 2025-05-02 at 16:38.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21900 on 2025-10-19 at 18:09:39","Large language models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks. However, their tendency to generate fluent yet unverifiable statements poses a fundamental challenge for deployment in high-stakes domains such as medicine, law, and education. This thesis addresses the central question of \\textit{verifiability}: how can LLMs produce outputs that are not only accurate but also supported by transparent, checkable evidence? Focusing on the concrete case of medical question answering (QA), this work investigates citation generation as a mechanism for enhancing verifiability. Rather than adhering to a fixed pipeline, the thesis follows an iterative, design-driven approach to evaluate how system-level decisions—including the use of parametric versus non-parametric knowledge, retrieval-augmented generation (RAG), and fine-grained attribution strategies—affect the alignment between model-generated content and external sources. Based on these insights, a two-pass citation framework is proposed. The approach first encourages in-context citation generation during answer formulation, followed by a post hoc retrieval and reranking stage that refines attribution at the statement level. This pipeline improves citation recall and precision while maintaining fluency and factual correctness. Additionally, a human annotation study reveals that recent general-purpose LLMs can serve as effective automatic judges of citation quality, often outperforming domain-specific NLI models in aligning with expert judgments. In summary, this thesis contributes both practical methods and conceptual frameworks for improving LLM verifiability in biomedical QA, with broader implications for developing trustworthy, evidence-supported AI in other knowledge-intensive fields."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129236"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Xiao Wang"],"dc:subject":["Large Language Models","Retrieval-Augmented Generation","Trustworthy AI","Verifiability","Citation Generation","Biomedical Question Answering"],"dc:title":["Enhancing the verifiability of large language model based medical question answering systems"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:04Z"}