AIware 2024
Mon 15 - Tue 16 July 2024 Porto de Galinhas, Brazil, Brazil
co-located with FSE 2024
Tue 16 Jul 2024 11:30 - 11:40 at Mandacaru - Industry Talk3 + AIware for Code Chair(s): Yiling Lou

Transformer-based language models are highly effective for code completion, with much research dedicated to enhancing the content of these completions. Despite their effectiveness, these models come with high operational costs and can be intrusive, especially when they suggest too often and interrupt developers who are concentrating on their work. Current research largely overlooks how these models interact with developers in practice and neglects to address when a developer should receive completion suggestions. To tackle this issue, we developed a machine learning model that can accurately predict when to invoke a code completion tool given the code context and available telemetry data.

To do so, we collect a dataset of 200k developer interactions with our cross-IDE code completion plugin and train several invocation filtering models. Our results indicate that our small-scale transformer model significantly outperforms the baseline while maintaining low enough latency. We further explore the search space for integrating additional telemetry data into a pre-trained transformer directly and obtain promising results. To further demonstrate our approach’s practical potential, we deployed the model in an online environment with 34 developers and provided real-world insights based on 74k actual invocations.

Tue 16 Jul

Displayed time zone: Brasilia, Distrito Federal, Brazil change

11:00 - 12:30
Industry Talk3 + AIware for CodeMain Track / Industry Statements and Demo Track at Mandacaru
Chair(s): Yiling Lou Fudan University
11:00
20m
Industry talk
AI-assisted User Intent Formalization for Programs: Problem and Applications
Industry Statements and Demo Track
Shuvendu K. Lahiri Microsoft Research
11:20
10m
Paper
Identifying the Factors That Influence Trust in AI Code CompletionACM SIGSOFT Distinguished Paper Award
Main Track
Adam Brown Google, Sarah D'Angelo Google, Ambar Murillo Google, Ciera Jaspan Google, Collin Green Google
DOI
11:30
10m
Paper
A Transformer-Based Approach for Smart Invocation of Automatic Code CompletionACM SIGSOFT Distinguished Paper Award
Main Track
Aral de Moor Delft University of Technology, Arie van Deursen Delft University of Technology, Maliheh Izadi Delft University of Technology
DOI
11:40
10m
Paper
Leveraging Machine Learning for Optimal Object-Relational Database Mapping in Software Systems
Main Track
Sasan Azizian University of Nebraska-Lincoln, Elham Rastegari Creighton University, Hamid Bagheri University of Nebraska-Lincoln
DOI
11:50
10m
Paper
Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs
Main Track
Sylvain Kouemo Ngassom Polytechnique Montréal, Arghavan Moradi Dakhel Polytechnique Montreal, Florian Tambon Polytechnique Montréal, Foutse Khomh Polytechnique Montréal
DOI
12:00
30m
Live Q&A
Session Q&A and topic discussions
Main Track