Rethinking Software Engineering in the Era of Foundation Models
Foundation models (FMs), such as Large Language Models (LLMs), have revolutionized software development by enabling new use cases and business models. We refer to software built using FMs as FMware. The unique properties of FMware (e.g., prompts, agents and the need for orchestration), coupled with the intrinsic limitations of FMs (e.g., hallucination) lead to a completely new set of software engineering challenges. Based on our experience, we pinpoint ten key SE4FMware challenges that have caused enterprise FMware development to be unproductive, costly, and risky. For each of those challenges, we state the path for innovation that we envision. We hope that the disclosure of the challenges will not only raise awareness but also promote deeper and further discussions, knowledge sharing, and innovative solutions.
Thu 18 JulDisplayed time zone: Brasilia, Distrito Federal, Brazil change
16:00 - 18:00 | AI4SE 3Industry Papers / Demonstrations / Journal First at Pitomba Chair(s): Maliheh Izadi Delft University of Technology | ||
16:00 18mTalk | Rethinking Software Engineering in the Era of Foundation Models Industry Papers Ahmed E. Hassan Queen’s University, Dayi Lin Centre for Software Excellence, Huawei Canada, Gopi Krishnan Rajbahadur Centre for Software Excellence, Huawei, Canada, Keheliya Gallaba Centre for Software Excellence, Huawei Canada, Filipe Cogo Centre for Software Excellence, Huawei Canada, Boyuan Chen Centre for Software Excellence, Huawei Canada, Haoxiang Zhang Huawei, Kishanthan Thangarajah Centre for Software Excellence, Huawei Canada, Gustavo Oliva Centre for Software Excellence, Huawei Canada, Jiahuei (Justina) Lin Centre for Software Excellence, Huawei Canada, Wali Mohammad Abdullah Centre for Software Excellence, Huawei Canada, Zhen Ming (Jack) Jiang York University | ||
16:18 18mTalk | LM-PACE: Confidence Estimation by Large Language Models for Effective Root Causing of Cloud Incidents Industry Papers Shizhuo Zhang University of Illinois Urbana-Champaign, Xuchao Zhang Microsoft, Chetan Bansal Microsoft Research, Pedro Las-Casas Microsoft, Rodrigo Fonseca Microsoft Research, Saravan Rajmohan Microsoft | ||
16:36 18mTalk | Application of Quantum Extreme Learning Machines for QoS Prediction of Elevators' Software in an Industrial Context Industry Papers Xinyi Wang Simula Research Laboratory and University of Oslo, Shaukat Ali Simula Research Laboratory and Oslo Metropolitan University, Aitor Arrieta Mondragon University, Paolo Arcaini National Institute of Informatics
, Maite Arratibel Orona | ||
16:54 18mTalk | X-lifecycle Learning for Cloud Incident Management using LLMs Industry Papers Drishti Goel Microsoft, Fiza Husain Microsoft, Aditya Kumar Singh Microsoft, Supriyo Ghosh Microsoft, Anjaly Parayil Microsoft, Chetan Bansal Microsoft Research, Xuchao Zhang Microsoft, Saravan Rajmohan Microsoft Media Attached | ||
17:12 18mTalk | Neat: Mobile App Layout Similarity Comparison based on Graph Convolutional Networks Industry Papers Zhu Tao ByteDance, Yongqiang Gao ByteDance, Jiayi Qi ByteDance, Chao Peng ByteDance, China, Qinyun Wu Bytedance Ltd., Xiang Chen ByteDance, Ping Yang Bytedance Network Technology | ||
17:30 18mTalk | Transformers and Meta-Tokenization in Sentiment Analysis for Software Engineering Journal First Nathan Cassee Eindhoven University of Technology, Andrei Agaronian Eindhoven University of Technology, Eleni Constantinou University of Cyprus, Nicole Novielli University of Bari, Alexander Serebrenik Eindhoven University of Technology | ||
17:48 9mTalk | EM-Assist: Safe automated ExtractMethod refactoring with LLMs Demonstrations Dorin Pomian University of Colorado Boulder, Abhiram Bellur University of Colorado Boulder, Malinda Dilhara University of Colorado Boulder, Zarina Kurbatova JetBrains Research, Egor Bogomolov JetBrains Research, Andrey Sokolov JetBrains Research, Timofey Bryksin JetBrains Research, Danny Dig University of Colorado Boulder, JetBrains Research Pre-print | ||