MoonBit: Explore the Design of an AI-Friendly Programming Language (LLM4Code 2024) - ICSE 2024

MoonBit: Explore the Design of an AI-Friendly Programming Language (LLM4Code 2024) - ICSE 2024

Fri 12 - Sun 21 April 2024 Lisbon, Portugal

Who

Track

When

Sat 20 Apr 2024 15:14 - 15:22 at Luis de Freitas Branco- Session 3: Keynote 2 + Position Papers Chair(s): Lingming Zhang

Abstract

MoonBit, a new general-purpose programming language designed for cloud and edge computing, was initiated in late 2022, coinciding with the announcement of ChatGPT. Language models like GPT, capable of producing practical programs, are revolutionizing the way we write programs and interact with computers. However, significant challenges persist, such as the models’ inability to understand the global context of a whole project with its dependencies, the need for human verification and correction of generated code, and the lack of assurance in meeting basic requirements like syntactic correctness.

In this paper, we explore the design of the MoonBit language highlighting its AI integration, emphasizing the synergy between traditional code intelligence and large language model capabilities. We also introduce a real-time, semantics-based sampler to guide the inference process of language models. This approach ensures the generated programs are both syntactically correct and free from obvious semantic flaws, such as type errors. Crucially, this has been achieved with minimal impact on overall performance. Our evaluation demonstrates a notable improvement in code quality, achieved without sacrificing the models’ responsiveness.

Link to Preprint

Haoxiang Fei
International Digital Economy Academy
Yu Zhang
International Digital Economy Academy
Hongbo Zhang
International Digital Economy Academy
Yanlin Wang
Sun Yat-sen University
China
Qing Liu
International Digital Economy Academy

Session Program

Sat 20 AprDisplayed time zone: Lisbon change

14:00 - 15:30Session 3: Keynote 2 + Position Papers LLM4Code at Luis de Freitas Branco Chair(s): Lingming Zhang University of Illinois at Urbana-Champaign
14:00 50m KeynoteOpen development of Large Language Models for code with BigCode and StarCoder2 LLM4Code Loubna Ben Allal Hugging Face
14:50 8m TalkBenchmarking the Security Aspect of Large Language Model-Based Code Generation LLM4Code Cheng Cheng Concordia University, Jinqiu Yang Concordia University Pre-print
14:58 8m TalkEnhancing LLM-Based Coding Tools through Native Integration of IDE-Derived Static Context LLM4Code Yichen LI The Chinese University of Hong Kong, Yun Peng The Chinese University of Hong Kong, Yintong Huo The Chinese University of Hong Kong, Michael Lyu The Chinese University of Hong Kong Pre-print
15:06 8m TalkEvaluating Fault Localization and Program Repair Capabilities of Existing Closed-Source General-Purpose LLMs LLM4Code Shengbei Jiang Beijing Jiaotong University, Jiabao Zhang Beijing Jiaotong University, Wei Chen Beijing Jiaotong University, Bo Wang Beijing Jiaotong University, Jianyi Zhou Huawei Cloud Computing Technologies Co., Ltd., Jie M. Zhang King’s College London Pre-print
15:14 8m TalkMoonBit: Explore the Design of an AI-Friendly Programming Language LLM4Code Haoxiang Fei International Digital Economy Academy, Yu Zhang International Digital Economy Academy, Hongbo Zhang International Digital Economy Academy, Yanlin Wang Sun Yat-sen University, Qing Liu International Digital Economy Academy Pre-print
15:22 8m TalkToward a New Era of Rapid Development: Assessing GPT-4-Vision’s Capabilities in UML-Based Code Generation LLM4Code Gabor Antal University of Szeged, Richárd Vozár Department of Software Engineering, University of Szeged, Hungary, Rudolf Ferenc University of Szeged

xWed 29 Jul 06:18