Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and utility (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Finally, we emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. Knowing the specific trustworthy technologies that have been employed is crucial for analyzing their effectiveness.

翻译：大型语言模型（LLMs），以ChatGPT为代表，因其出色的自然语言处理能力而备受关注。然而，这些LLMs也带来了诸多挑战，尤其是在可信度方面。因此，确保LLMs的可信度成为一个重要课题。本文介绍了TrustLLM，这是一项关于LLMs可信度的全面研究，涵盖可信度不同维度的原则、针对主流LLMs可信度的既定基准测试、评估与分析，以及对开放挑战与未来方向的探讨。具体而言，我们首先为可信LLMs提出了一套涵盖八个不同维度的原则。基于这些原则，我们进一步建立了涵盖六个维度（包括真实性、安全性、公平性、稳健性、隐私性和机器伦理）的基准测试。随后，我们呈现了一项研究，评估了TrustLLM中16个主流LLMs，涉及超过30个数据集。我们的发现首先表明，总体而言，可信度与实用性（即功能有效性）呈正相关。其次，我们的观察揭示了专有LLMs在可信度方面通常优于大多数开源同类模型，这引发了对广泛可访问的开源LLMs潜在风险的担忧。不过，少数开源LLMs已非常接近专有模型的表现。第三，需注意某些LLMs可能过度校准以表现出可信度，以至于将良性提示错误视为有害而拒绝回应，从而损害其实用性。最后，我们强调不仅要在模型本身，还要在支撑可信度的技术中确保透明度至关重要。了解所采用的具体可信技术，对于分析其有效性十分关键。