她有着钴蓝色的眼睛：通过提示测试构建对齐且可持续的语言模型
She had Cobalt Blue Eyes: Prompt Testing to Create Aligned and Sustainable Language Models
AI总结：
针对大语言模型伦理风险与对齐难题，本研究提出提示测试套件，覆盖开发全流程，评估四款前沿模型后发现其与社会对齐存在差距，且该方案可降低模型安全化的环境成本。
摘要：
随着大语言模型（LLMs）在社会中的应用日益广泛，其被滥用的风险也随之上升。必须建立适当的保障机制，确保大语言模型的输出符合社会伦理标准，彰显人工智能技术的积极作用。近期事件显示，传统训练的大语言模型存在伦理问题，整体导致用户体验不安全。这引出了我们的研究问题：如何确保大语言模型的对齐性？本研究中，我们提出了一套由独特提示构成的测试套件，以推动开发公平、安全、鲁棒的对齐大语言模型。我们证明，在开发流程的每个环节（包括数据整理、预训练和微调）对大语言模型使用提示工程，将使模型整体更具责任感。我们的测试套件评估了四款前沿语言模型的输出：GPT-3.5、GPT-4、OPT 和 LLaMA-2。本文的评估凸显了社会对齐要求与当前大语言模型能力之间的差距。此外，部署我们这类测试套件可降低保障模型安全公平的环境成本。
英文摘要：
As the use of large language models (LLMs) increases within society, as does the risk of their misuse. Appropriate safeguards must be in place to ensure LLM outputs uphold the ethical standards of society, highlighting the positive role that artificial intelligence technologies can have. Recent events indicate ethical concerns around conventionally trained LLMs, leading to overall unsafe user experiences. This motivates our research question: how do we ensure LLM alignment? In this work, we introduce a test suite of unique prompts to foster the development of aligned LLMs that are fair, safe, and robust. We show that prompting LLMs at every step of the development pipeline, including data curation, pre-training, and fine-tuning, will result in an overall more responsible model. Our test suite evaluates outputs from four state-of-the-art language models: GPT-3.5, GPT-4, OPT, and LLaMA-2. The assessment presented in this paper highlights a gap between societal alignment and the capabilities of current LLMs. Additionally, implementing a test suite such as ours lowers the environmental overhead of making models safe and fair.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
