2023 · 37 citations · 15 references
ComputingComputer ScienceArtificial IntelligenceProgramming LanguagesSoftware EngineeringAbstract Syntax TreesCode GenerationControl-flow AnalysisLanguage ModelingNatural Language GenerationText GenerationControl Logic GenerationControl Logic ModelingExploratory Case StudyNatural Language InterfacesPlc Programming LanguagesPrompt-based GenerationStructured Text ProgrammingSyntax-directed Code Generation
Large language models (LLMs) providing generative AI have become popular to support software engineers in creating, summarizing, optimizing, and documenting source code. It is still unknown how LLMs can support control engineers using typical control programming languages in programming tasks. Researchers have explored GitHub CoPilot or DeepMind AlphaCode for source code generation but did not yet tackle control logic programming. A key contribution of this paper is an exploratory study, for which we created 100 LLM prompts in 10 representative categories to analyze control logic generation for of PLCs and DCS from natural language. We tested the prompts by generating answers with ChatGPT using the GPT-4 LLM. It generated syntactically correct IEC 61131-3 Structured Text code in many cases and demonstrated useful reasoning skills that could boost control engineer productivity. Our prompt collection is the basis for a more formal LLM benchmark to test and compare such models for control logic generation.
15
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
Jules White, Quchen Fu, Sam Hays et al. · arXiv (Cornell University) · 2023 · 792 citations · Full text
Computing, Computer Science, Natural Language Processing +12
A Categorical Archive of ChatGPT Failures
Ali Borji · Research Square · 2023 · 421 citations · Full text