Analyzing the Impact of Context Representation and Scope in Code Infilling
Existing studies solve software engineering tasks using code infilling through LLMC. They utilize context information, which refers to data near the target code of infilling, as input prompts. Although prompts are essential for infilling the target code, current studies use them without analyzing the impact of the representation and scope of context on code infilling. In this study, we analyzed how context representation and scope affect the performance of code infilling. We used XLCost, which contains code, comments, and a function comment for various programming languages. The combination of code and a function comment for context representation yielded the best code infilling performance. Furthermore, we found that the context scope is proportional to performance. Our analysis results can be applied in various tasks that involve code infilling in the future.
Thu 18 AprDisplayed time zone: Lisbon change
10:30 - 11:00 | |||
10:30 30mPoster | Unleashing the Power of Clippy in Real-World Rust Projects Posters Chunmiao Li National Institute of Informatics, Yijun Yu The Open University, UK, Haitao Wu Huawei Technologies Canada, Luca Carlig Huawei Ireland Research Center, Shijie Nie Fujitsu R&D Center, Lingxiao Jiang Singapore Management University | ||
10:30 30mPoster | The Impact of a Live Refactoring Environment on Software Development Posters Sara Fernandes FEUP, Universidade do Porto, Ademar Aguiar Faculty of Engineering, University of Porto & INESC TEC, André Restivo LIACC, Universidade do Porto, Porto, Portugal | ||
10:30 30mPoster | Tracking assets in source code with Security Annotations Posters Daniel Haak Augsburg Technical University of Applied Sciences, Raphael Mayr Augsburg Technical University of Applied Sciences, Jan-Philipp Steghöfer XITASO GmbH IT & Software Solutions, Alexandra Teynor Augsburg Technical University of Applied Sciences, Phillip Heidegger Augsburg Technical University of Applied Sciences | ||
10:30 30mPoster | eAIEDF: Extended AI Error Diagnosis Flowchart for Automatically Identifying Misprediction Causes in Production Models Posters | ||
10:30 30mPoster | SLIM: a Scalable and Interpretable Light-weight Fault Localization Algorithm for Imbalanced Data in Microservice Posters Rui Ren DAMO Academy, Alibaba Group Hangzhou, China, Jingbang Yang DAMO Academy, Alibaba Group Hangzhou, China, Linxiao Yang DAMO Academy, Alibaba Group Hangzhou, China, Xinyue Gu DAMO Academy, Alibaba Group Hangzhou, China, Liang Sun DAMO Academy, Alibaba Group Hangzhou, China | ||
10:30 30mPoster | Designing Digital Twins for Enhanced Reusability Posters | ||
10:30 30mPoster | MUFIN: Improving Neural Repair Models with Back-Translation Posters André Silva KTH Royal Institute of Technology, João F. Ferreira INESC-ID and IST, University of Lisbon, He Ye Carnegie Mellon University, Martin Monperrus KTH Royal Institute of Technology | ||
10:30 30mPoster | Blocks? Graphs? Why Not Both? Designing and Evaluating a Hybrid Programming Environment for End-users Posters Nico Ritschel University of British Columbia, Felipe Fronchetti Virginia Commonwealth University, Reid Holmes University of British Columbia, Ronald Garcia University of British Columbia, David C. Shepherd Louisiana State University | ||
10:30 30mPoster | Fault Localization on Verification Witnesses Posters | ||
10:30 30mPoster | Analyzing the Impact of Context Representation and Scope in Code Infilling Posters | ||
10:30 30mPoster | Hunting DeFi Vulnerabilities via Context-Sensitive Concolic Verification Posters Yepeng Ding University of Tokyo, Arthur Gervais Imperial College London, Roger Wattenhofer ETHZ, Hiroyuki Sato The University of Tokyo DOI Pre-print Media Attached | ||
10:30 30mPoster | Exploring the Computational Complexity of SAT Counting and Uniform Sampling with Phase Transitions Posters Olivier Zeyen University of Luxembourg, SnT, Maxime Cordy University of Luxembourg, Luxembourg, Gilles Perrouin Fonds de la Recherche Scientifique - FNRS & University of Namur, Mathieu Acher University of Rennes, France / Inria, France / CNRS, France / IRISA, France | ||
10:30 30mPoster | GRAIL: Checking Transaction Isolation Violations with Graph Queries Posters Stefania Dumbrava ENSIIE & Institut Polytechnique de Paris, Zhao Jin ENSIIE, Burcu Kulahcioglu Ozkan Delft University of Technology, Jingxuan Qiu Delft University of Technology |