arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.12095cs.AIcs.CLcs.LG
收藏

论ChatGPT的鲁棒性:对抗性与分布外视角

On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective

Microsoft Research(微软研究院);City University of Hong Kong(香港城市大学);Microsoft STCA(微软中国区软件工程技术中心);Carnegie Mellon University(卡内基梅隆大学);Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳));Peking University(北京大学);Westlake University(西湖大学)

Jindong Wang, Xixu Hu, Wenxin Hou, Hao Chen, Runkai Zheng, Yidong Wang, Linyi Yang, Haojun Huang, Wei Ye, Xiubo Geng, Binxin Jiao, Yue Zhang, Xing Xie

AI总结:

本文从对抗性和分布外视角全面评估ChatGPT的鲁棒性,发现其在多数任务上优于基线模型,但绝对性能仍有不足,且医学任务回答偏非正式,并探讨了未来研究方向。

摘要:

ChatGPT是OpenAI近期发布的聊天机器人服务,在过去几个月中受到越来越多的关注。虽然对ChatGPT各方面性能的评估已经开展,但其鲁棒性,即对意外输入的表现,对公众而言仍不明确。在负责任的人工智能中,鲁棒性尤其受到关注,特别是对于安全关键型应用。在本文中,我们从对抗性和分布外(OOD)的角度对ChatGPT的鲁棒性进行了全面评估。为此,我们采用AdvGLUE和ANLI基准来评估对抗鲁棒性,并使用Flipkart评论和DDXPlus医学诊断数据集进行OOD评估。我们选择了几种流行的基础模型作为基线。结果表明,ChatGPT在大多数对抗性和分布外的分类及翻译任务上表现出持续的优势。然而,其绝对性能远非完美,这表明对抗性和分布外鲁棒性对基础模型仍构成重大威胁。此外,ChatGPT在理解对话相关文本方面表现出惊人的性能,我们发现它倾向于为医学任务提供非正式建议而非明确答案。最后,我们对可能的研究方向进行了深入讨论。

英文摘要:

ChatGPT is a recent chatbot service released by OpenAI and is receiving increasing attention over the past few months. While evaluations of various aspects of ChatGPT have been done, its robustness, i.e., the performance to unexpected inputs, is still unclear to the public. Robustness is of particular concern in responsible AI, especially for safety-critical applications. In this paper, we conduct a thorough evaluation of the robustness of ChatGPT from the adversarial and out-of-distribution (OOD) perspective. To do so, we employ the AdvGLUE and ANLI benchmarks to assess adversarial robustness and the Flipkart review and DDXPlus medical diagnosis datasets for OOD evaluation. We select several popular foundation models as baselines. Results show that ChatGPT shows consistent advantages on most adversarial and OOD classification and translation tasks. However, the absolute performance is far from perfection, which suggests that adversarial and OOD robustness remains a significant threat to foundation models. Moreover, ChatGPT shows astounding performance in understanding dialogue-related texts and we find that it tends to provide informal suggestions for medical tasks instead of definitive answers. Finally, we present in-depth discussions of possible research directions.

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。

↑