arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.05561cs.CL
收藏

TrustLLM:大语言模型中的可信度研究

TrustLLM: Trustworthiness in Large Language Models

Lehigh University(利哈伊大学);University of Notre Dame(圣母大学);Illinois Institute of Technology(伊利诺伊理工大学);CISPA(CISPA亥姆霍兹信息安全研究中心);University of Cambridge(剑桥大学);Institut Polytechnique de Paris(巴黎综合理工学院);William & Mary(威廉玛丽学院);Texas A&M University(德克萨斯农工大学);University of Georgia(佐治亚大学);Samsung Research America(三星美国研究院);Stanford University(斯坦福大学);University of Oxford(牛津大学)
Yue Huang, Lichao Sun, Haoran Wang, Siyuan Wu, Qihui Zhang, Yuan Li, Chujie Gao, Yixin Huang, Wenhan Lyu, Yixuan Zhang, Xiner Li, Zhengliang Liu, Yixin Liu, Yij… 展开作者

Yue Huang, Lichao Sun, Haoran Wang, Siyuan Wu, Qihui Zhang, Yuan Li, Chujie Gao, Yixin Huang, Wenhan Lyu, Yixuan Zhang, Xiner Li, Zhengliang Liu, Yixin Liu, Yijue Wang, Zhikun Zhang, Bertie Vidgen, Bhavya Kailkhura, Caiming Xiong, Chaowei Xiao, Chunyuan Li, Eric Xing, Furong Huang, Hao Liu, Heng Ji, Hongyi Wang, Huan Zhang, Huaxiu Yao, Manolis Kellis, Marinka Zitnik, Meng Jiang, Mohit Bansal, James Zou, Jian Pei, Jian Liu, Jianfeng Gao, Jiawei Han, Jieyu Zhao, Jiliang Tang, Jindong Wang, Joaquin Vanschoren, John Mitchell, Kai Shu, Kaidi Xu, Kai-Wei Chang, Lifang He, Lifu Huang, Michael Backes, Neil Zhenqiang Gong, Philip S. Yu, Pin-Yu Chen, Quanquan Gu, Ran Xu, Rex Ying, Shuiwang Ji, Suman Jana, Tianlong Chen, Tianming Liu, Tianyi Zhou, William Wang, Xiang Li, Xiangliang Zhang, Xiao Wang, Xing Xie, Xun Chen, Xuyu Wang, Yan Liu, Yanfang Ye, Yinzhi Cao, Yong Chen, Yue Zhao

AI总结:

本文提出TrustLLM框架,从八个维度定义可信原则并构建六维基准,评估16个主流大语言模型在30多个数据集上的表现,揭示可信度与实用性的关系及开源模型的风险。

摘要:

以ChatGPT为代表的大语言模型(LLMs)因其出色的自然语言处理能力而受到广泛关注。然而,这些大语言模型也带来了许多挑战,尤其是在可信度方面。因此,确保大语言模型的可信度成为一个重要课题。本文介绍了TrustLLM,这是一项关于大语言模型可信度的综合研究,涵盖不同可信度维度的原则、已建立的基准、对主流大语言模型可信度的评估与分析,以及对开放性挑战和未来方向的讨论。具体而言,我们首先提出了一套涵盖八个不同维度的可信大语言模型原则。基于这些原则,我们进一步建立了一个跨越六个维度的基准,包括真实性、安全性、公平性、鲁棒性、隐私和机器伦理。随后,我们展示了一项在TrustLLM中评估16个主流大语言模型的研究,该研究包含30多个数据集。我们的研究结果首先表明,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,专有大语言模型在可信度方面通常优于大多数开源同类模型,这引发了人们对广泛可获取的开源大语言模型潜在风险的担忧。然而,少数开源大语言模型的表现已非常接近专有模型。第三,需要指出的是,一些大语言模型可能被过度校准为表现出可信度,以至于它们因将良性提示误判为有害提示而不予回应,从而损害了其实用性。最后,我们强调不仅要在模型本身中确保透明性,还要在支撑可信度的技术中确保透明性。了解所采用的具体可信技术对于分析其有效性至关重要。

英文摘要:

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.

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。

↑