An Ensemble Method for Bug Triaging using Large Language Models
Thu 18 Apr 2024 11:00 - 11:12 at Vianna da Motta - SRC Presentations Chair(s): Mattia Fazzini, André Restivo
This study delves into the automation of bug triaging — the process of assigning bug reports to appropriate developers and components in software development. At the core of our investigation are six transformer-based Large Language Models (LLMs), which we fine-tuned using a sequence classification method tailored for bug triaging tasks. Our results demonstrate a noteworthy performance of the DeBERTa model, which significantly outperforms its counterparts CodeBERT, DistilBERT, RoBERTa, ALBERT, and BERT in terms of effectiveness. However, it is crucial to note that despite the varying performance of each model, each model exhibits a unique degree of orthogonality, indicating distinct strengths in their bug triaging capabilities. Leveraging these orthogonal characteristics, we propose an ensemble method combining these LLMs through voting and stacking techniques. Remarkably, our findings reveal that the voting-based ensemble method surpasses all individual baselines in performance.
Wed 17 AprDisplayed time zone: Lisbon change
16:00 - 17:30 | SRC PostersSRC - ACM Student Research Competition at Open Space Chair(s): Mattia Fazzini University of Minnesota, André Restivo LIACC, Universidade do Porto, Porto, Portugal | ||
16:00 90mPoster | Program Decomposition and Translation with Static Analysis SRC - ACM Student Research Competition Ali Reza Ibrahimzada University of Illinois Urbana-Champaign DOI Pre-print File Attached | ||
16:00 90mPoster | IntTracer: Sanitization-aware IO2BO Vulnerability Detection across Codebases SRC - ACM Student Research Competition Xiang Chen Shanghai Jiao Tong University | ||
16:00 90mPoster | Vulnerability Root Cause Function Locating For Java Vulnerabilities SRC - ACM Student Research Competition Lyuye Zhang Nanyang Technological University | ||
16:00 90mPoster | Flakiness Repair in the Era of Large Language Models SRC - ACM Student Research Competition Yang Chen University of Illinois at Urbana-Champaign | ||
16:00 90mPoster | Refining Abstract Specifications into Dangerous Traffic Scenarios SRC - ACM Student Research Competition Aren Babikian McGill University | ||
16:00 90mPoster | An Ensemble Method for Bug Triaging using Large Language Models SRC - ACM Student Research Competition Atish Kumar Dipongkor University of Central Florida | ||
16:00 90mPoster | Classifying Source Code: How Far Can Compressor-based Classifiers Go? SRC - ACM Student Research Competition Zhou Yang Singapore Management University | ||
Thu 18 AprDisplayed time zone: Lisbon change
11:00 - 12:30 | SRC PresentationsSRC - ACM Student Research Competition at Vianna da Motta Chair(s): Mattia Fazzini University of Minnesota, André Restivo LIACC, Universidade do Porto, Porto, Portugal | ||
11:00 12mPoster | An Ensemble Method for Bug Triaging using Large Language Models SRC - ACM Student Research Competition Atish Kumar Dipongkor University of Central Florida | ||
11:12 12mPoster | Classifying Source Code: How Far Can Compressor-based Classifiers Go? SRC - ACM Student Research Competition Zhou Yang Singapore Management University | ||
11:24 12mPoster | Flakiness Repair in the Era of Large Language Models SRC - ACM Student Research Competition Yang Chen University of Illinois at Urbana-Champaign | ||
11:36 12mPoster | Program Decomposition and Translation with Static Analysis SRC - ACM Student Research Competition Ali Reza Ibrahimzada University of Illinois Urbana-Champaign DOI Pre-print File Attached | ||
11:48 12mPoster | Refining Abstract Specifications into Dangerous Traffic Scenarios SRC - ACM Student Research Competition Aren Babikian McGill University | ||
