Concept-Guided LLM Agents for Human-AI Safety Codesign

arXiv:2404.15317v1 Announce Type: cross
Abstract: Generative AI is increasingly important in software engineering, including safety engineering, where its use ensures that software does not cause harm to people. This also leads to high quality requirements for generative AI. Therefore, the simplistic use of Large Language Models (LLMs) alone will not meet these quality demands. It is crucial to develop more advanced and sophisticated approaches that can effectively address the complexities and safety concerns of software systems. Ultimately, humans must understand …

abstract agents arxiv concept cs.hc cs.lg cs.se engineering generative harm human language language models large language large language models leads llm llms people quality requirements safety safety engineering software software engineering type will