[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-246020-105":53,"doc-detail-246020-en":126},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":119,"head_meta":121,"extra_data":123,"updated_unix":125},105,"en","can-we-enhance-bug-report-quality-using-llms-an-empirical-study-of-llm-based-bug-report-generation-ease-2025","Can We Enhance Bug Report Quality Using LLMs? - An Empirical Study of LLM-Based Bug Report Generation - EASE 2025","","Bug reports guide developers in triage and fixing, yet unclear, incomplete, or ambiguous descriptions often cause delays and heavy manual effort. This paper investigates whether instruction fine-tuned large language models can convert casual, unstructured bug reports into structured reports that follow a standard template. Three open-source models (Qwen 2.5, Mistral, Llama 3.2) are evaluated against ChatGPT-4o using CTQRS, ROUGE, METEOR, and SBERT. Fine-tuned Qwen 2.5 reaches 77% CTQRS, with strong F1 for step-to-reproduce, and good generalization to unseen projects.",{"@graph":63,"@context":118},[64,80,101],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":11,"@type":70,"position":76},"https://docshare.wps.com/template/presentations/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/can-we-enhance-bug-report-quality-using-llms-an-empirical-study-of-llm-based-bug-report-generation-ease-2025/246020/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/can-we-enhance-bug-report-quality-using-llms-an-empirical-study-of-llm-based-bug-report-generation-ease-2025/246020.png","ImageObject",442,249,{"name":88,"@type":89},"Eliana","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-10-21","2026-09-12",true,{"@type":98,"interactionType":99,"userInteractionCount":40},"InteractionCounter",{"@type":100},"ViewAction",{"@type":102,"mainEntity":103},"FAQPage",[104,110,114],{"name":105,"@type":106,"acceptedAnswer":107},"How does the study improve bug report quality using LLMs?","Question",{"text":108,"@type":109},"The paper evaluates instruction fine-tuned LLMs to transform unstructured bug reports into structured ones that match a standard template, while highlighting missing information before submission.","Answer",{"name":111,"@type":106,"acceptedAnswer":112},"Which models and baselines are compared in the experiments?",{"text":113,"@type":109},"The study compares three open-source instruction-tuned LLMs (Qwen 2.5, Mistral, and Llama 3.2) against ChatGPT-4o using established evaluation metrics.",{"name":115,"@type":106,"acceptedAnswer":116},"What do the results show about model performance and generalization?",{"text":117,"@type":109},"Fine-tuned Qwen 2.5 achieves the highest CTQRS score (77%), and the approach generalizes to unseen projects, reaching up to 70% CTQRS on other popular codebases.","https://schema.org",{"og:url":78,"og:type":120,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":122,"canonical":78},"index,follow",{"doc_id":124,"site_id":56},246020,1791415510,{"code":4,"msg":5,"data":127},{"doc_id":124,"user_id":128,"nickname":88,"user_avatar":129,"doc_module":9,"category_id":8,"category_name":11,"doc_title":59,"doc_description":61,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":40,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":135,"language":136,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":137,"faqs":138,"seo_title":139,"seo_description":61,"update_tm":140,"read_time":79},4398048949847,"https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267","Can We Enhance Bug Report Quality Using LLMs?: An Empirical Study of LLM-Based Bug Report Generation  \nJagrit Acharya  \nUniversity of Calgary Calgary, Canada jagrit.acharya1@ucalgary.ca  \nGouri Ginde  \nUniversity of Calgary Calgary, Canada gouri.deshpande@ucalgary.ca  \narXiv :2504 . 18804v1 [ cs . SE] 26 Apr 2025  \nABSTRACT  \nBug reports contain the information developers need to triage and fix software bugs. However, unclear, incomplete, or ambiguous information may lead to delays and excessive manual effort spent on bug triage and resolution. In this paper, we explore whether Instruction fine-tuned Large Language Models (LLMs) can automatically transform casual, unstructured bug reports into high-quality, structured bug reports adhering to a standard template. We evaluate three open-source instruction-tuned LLMs (Qwen 2.5, Mistral, and Llama 3.2) against ChatGPT-4o, measuring performance on established metrics such as CTQRS, ROUGE, METEOR, and SBERT. Our experiments show that fine-tuned Qwen 2.5 achieves a CTQRS score of 77%, outperforming both fine-tuned Mistral (71%), Llama 3.2 (63%) and ChatGPT in 3-shot learning (75%) . Further analysis reveals that Llama 3.2 shows higher accuracy of detecting missing fields particularly Expected Behavior and Actual Behavior, while Qwen 2.5 demonstrates superior performance in capturing Stepsto-Reproduce, with an F1 score of 76% . Additional testing of the models on other popular projects (e.g., Eclipse, GCC) demonstrates that our approach generalizes well, achieving up to 70% CTQRS in unseen projects’ bug reports. These findings highlight the potential of instruction fine-tuning in automating structured bug report generation, reducing manual effort for developers and streamlining the software maintenance process.  \nCCS CONCEPTS  \n• Software and its engineering → Software maintenance tools.  \nKEYWORDS  \nBug report quality, large language models, instruction fine-tuning, software maintainance, and software engineering  \nACM Reference Format:  \nJagrit Acharya and Gouri Ginde. 2025. Can We Enhance Bug Report Quality Using LLMs?: An Empirical Study of LLM-Based Bug Report Generation. In Proceedings of The 29th International Conference on Evaluation and Assessment in Software Engineering (EASE 2025). ACM, New York, NY, USA, 10 pages. [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nEASE 2025, 17–20 June, 2025, Istanbul, Türkiye  \n© 2025 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-1-4503-XXXX-X/2018/06. . . $15.00 [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nCan We Enhance Bug Report Quality Using LLMs?: An Empirical Study of LLM-Based Bug Report Generation  \n1 INTRODUCTION  \nBug reports are essential in software maintenance, providing developers with critical information to identify, triage, and resolve software defects [76] . A bug report is a record of a software fault or defect that is created by an end-user or a tester [1] . However, the effectiveness of bug reports is often hindered by ambiguity, incompleteness, or inconsistency in the information provided by reporters [2, 36] . Well-structured reports that clearly articulate observed behavior (OB), expected behavior (EB), and steps to reproduce (S2Rs) minimize ambiguity and enable developers to resolve issues wi","cbCaii246sYNXYah","https://ap.wps.com/l/cbCaii246sYNXYah","pdf",1775507,10,"English","# Abstract\n# Introduction\n## Problem Motivation\n## Related Work\n## Research Aim and Contributions","[{\"question\":\"How does the study improve bug report quality using LLMs?\",\"answer\":\"The paper evaluates instruction fine-tuned LLMs to transform unstructured bug reports into structured ones that match a standard template, while highlighting missing information before submission.\"},{\"question\":\"Which models and baselines are compared in the experiments?\",\"answer\":\"The study compares three open-source instruction-tuned LLMs (Qwen 2.5, Mistral, and Llama 3.2) against ChatGPT-4o using established evaluation metrics.\"},{\"question\":\"What do the results show about model performance and generalization?\",\"answer\":\"Fine-tuned Qwen 2.5 achieves the highest CTQRS score (77%), and the approach generalizes to unseen projects, reaching up to 70% CTQRS on other popular codebases.\"}]","Can We Enhance Bug Report Quality Using LLMs? - An Empirical Study of LLM-Based Bug Report Generation - EASE 2025 | PDF",1789232790]