Generative Pre-trained Transformer (GPT) models have exhibited exciting progress in their capabilities, capturing the interest of practitioners and the public alike. Yet, while the literature on the trustworthiness of GPT models remains limited, practitioners have proposed employing capable GPT models for sensitive applications such as healthcare and finance -- where mistakes can be costly. To this end, this work proposes a comprehensive trustworthiness evaluation for large language models with a focus on GPT-4 and GPT-3.5, considering diverse perspectives -- including toxicity, stereotype bias, adversarial robustness, out-of-distribution robustness, robustness on adversarial demonstrations, privacy, machine ethics, and fairness. Based on our evaluations, we discover previously unpublished vulnerabilities to trustworthiness threats. For instance, we find that GPT models can be easily misled to generate toxic and biased outputs and leak private information in both training data and conversation history. We also find that although GPT-4 is usually more trustworthy than GPT-3.5 on standard benchmarks, GPT-4 is more vulnerable given jailbreaking system or user prompts, potentially because GPT-4 follows (misleading) instructions more precisely. Our work illustrates a comprehensive trustworthiness evaluation of GPT models and sheds light on the trustworthiness gaps. Our benchmark is publicly available at https://decodingtrust.github.io/; our dataset can be previewed at https://huggingface.co/datasets/AI-Secure/DecodingTrust; a concise version of this work is at https://openreview.net/pdf?id=kaHpo8OZw2.

翻译：生成式预训练Transformer（GPT）模型在能力上展现出令人振奋的进步，吸引了从业者和公众的关注。然而，尽管关于GPT模型可信度的文献仍然有限，从业者已提议将具备强大能力的GPT模型应用于医疗和金融等敏感领域——这些领域中的失误代价高昂。为此，本研究提出针对大语言模型的可信度综合评估，重点关注GPT-4和GPT-3.5，涵盖多元视角，包括毒性、刻板印象偏见、对抗鲁棒性、分布外鲁棒性、对抗演示鲁棒性、隐私保护、机器伦理和公平性。基于我们的评估，我们发现了先前未公开的可信度威胁漏洞。例如，我们发现GPT模型容易被误导生成有毒和带有偏见的内容，并泄露训练数据和对话历史中的隐私信息。我们还发现，尽管GPT-4在标准基准测试中通常比GPT-3.5更可信，但GPT-4在遭受系统或用户提示的越狱攻击时更为脆弱，这可能是由于GPT-4更精确地遵循（误导性）指令。我们的工作展示了GPT模型的可信度综合评估，并揭示了可信度差距。我们的基准测试已公开发布于https://decodingtrust.github.io/；数据集预览地址为https://huggingface.co/datasets/AI-Secure/DecodingTrust；本文精简版参见https://openreview.net/pdf?id=kaHpo8OZw2。