AI语言模型对简单问题的可靠性下降,尽管在复杂任务方面表现更好,正如关于自然的一项研究所揭示的那样。 AI language models' reliability decreases for simple questions, despite better performance on complex tasks, as revealed by a study in Nature.
一项对自然的研究显示,先进的人工智能语言模式,如ChatGPT,在回答简单的问题时越来越不可靠,尽管在复杂的任务方面表现更好。 A study in Nature reveals that advanced AI language models, such as ChatGPT, are becoming less reliable in answering simple questions, despite performing better on complex tasks. 来自几个机构的研究人员发现,这些模型在他们不知道答案时往往不承认,导致信心错位。 Researchers from several institutions found that these models often fail to acknowledge when they don't know answers, leading to misplaced confidence. 该研究呼吁重新设计AI系统,纳入拒绝选择和人力监督,以提高准确性,帮助用户理解其局限性。 The study calls for redesigning AI systems to include rejection options and human oversight to enhance accuracy and help users understand their limitations.