{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/127392"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/127392","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Harnessing large language models for software engineering","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-12-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-12-01","abstract_has_math":false,"creators":["Wei, Yuxiang"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Zhang, Lingming"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-12-06","date_published":"2024-12-06","updated_at":"2026-07-22T22:25:04Z","subjects":["Large Language Models","Software Engineering","Program Synthesis","Automated Program Repair"],"languages":["en","eng"],"rights":["Copyright 2024 Yuxiang Wei"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/127392","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Zhang, Lingming"]},{"key":"dc:creator","label":"Author","values":["Wei, Yuxiang"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-12-06","2024-12"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"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 at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Large Language Models","Software Engineering","Program Synthesis","Automated Program Repair"]}]},{"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 2024 Yuxiang Wei"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/127392"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-12-01","The student, Yuxiang Wei, accepted the attached license on 2024-12-03 at 17:54.","The student, Yuxiang Wei, submitted this Thesis for approval on 2024-12-03 at 18:29.","This Thesis was approved for publication on 2024-12-06 at 13:18.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21482 on 2025-03-28 at 14:44:35","Automatic code generation, often referred to as program synthesis, has seen remarkable progress with the emergence of large language models (LLMs) trained on extensive datasets of text and programming-related data. This thesis examines the role that LLMs play in contemporary software engineering, with a particular focus on solving programming exercises, infilling code within existing projects, and automated program repair (APR). We begin by showing how effectively LLMs can address self-contained programming challenges. Using methods like step-by-step code synthesis and feedback-driven refinement, we show that the quality of solutions improves significantly when iterative processes are applied. Additionally, we present a novel framework, PairCoder, which leverages a collaborative approach to code generation. In this setup, two LLMs work together, adopting distinct roles: one acts as the driver to generate the core solutions, while the other serves as the navigator, providing guidance, critique, and suggestions. This iterative interplay between the two models results in more accurate and robust code by bringing multiple perspectives to the problem-solving process. When it comes to code infilling, we critically analyze existing methods for generating synthetic data and highlight their limitations when applied to more complex, real-world scenarios. To address these shortcomings, we propose adaptations to these techniques that allow LLMs to better understand and operate within intricate codebases. Lastly, we evaluate the capabilities of LLMs in the field of automated program repair. This includes a comparative analysis of models specialized for code infilling and those designed for sequence-to-sequence generation. We also perform data contamination analyses on popular benchmark datasets to understand the impact of training and testing data overlap on model performance. Through these investigations, this thesis highlights the promising potential of LLMs in addressing a wide range of software engineering challenges and offers insights into how these models can be further refined and optimized for real-world applications."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Harnessing large language models for software engineering"]}]}],"canonical_facts":{"dc:contributor":["Zhang, Lingming"],"dc:creator":["Wei, Yuxiang"],"dc:date":["2024-12-06","2024-12"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-12-01","The student, Yuxiang Wei, accepted the attached license on 2024-12-03 at 17:54.","The student, Yuxiang Wei, submitted this Thesis for approval on 2024-12-03 at 18:29.","This Thesis was approved for publication on 2024-12-06 at 13:18.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21482 on 2025-03-28 at 14:44:35","Automatic code generation, often referred to as program synthesis, has seen remarkable progress with the emergence of large language models (LLMs) trained on extensive datasets of text and programming-related data. This thesis examines the role that LLMs play in contemporary software engineering, with a particular focus on solving programming exercises, infilling code within existing projects, and automated program repair (APR). We begin by showing how effectively LLMs can address self-contained programming challenges. Using methods like step-by-step code synthesis and feedback-driven refinement, we show that the quality of solutions improves significantly when iterative processes are applied. Additionally, we present a novel framework, PairCoder, which leverages a collaborative approach to code generation. In this setup, two LLMs work together, adopting distinct roles: one acts as the driver to generate the core solutions, while the other serves as the navigator, providing guidance, critique, and suggestions. This iterative interplay between the two models results in more accurate and robust code by bringing multiple perspectives to the problem-solving process. When it comes to code infilling, we critically analyze existing methods for generating synthetic data and highlight their limitations when applied to more complex, real-world scenarios. To address these shortcomings, we propose adaptations to these techniques that allow LLMs to better understand and operate within intricate codebases. Lastly, we evaluate the capabilities of LLMs in the field of automated program repair. This includes a comparative analysis of models specialized for code infilling and those designed for sequence-to-sequence generation. We also perform data contamination analyses on popular benchmark datasets to understand the impact of training and testing data overlap on model performance. Through these investigations, this thesis highlights the promising potential of LLMs in addressing a wide range of software engineering challenges and offers insights into how these models can be further refined and optimized for real-world applications."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/127392"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 Yuxiang Wei"],"dc:subject":["Large Language Models","Software Engineering","Program Synthesis","Automated Program Repair"],"dc:title":["Harnessing large language models for software engineering"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:04Z"}