A robust decision-making process must take into account uncertainty, especially when the choice involves inherent risks. Because artificial intelligence (AI) systems are increasingly integrated into decision-making workflows, managing uncertainty relies more and more on the metacognitive capabilities of these systems; i.e, their ability to assess the reliability of and regulate their own decisions. Hence, it is crucial to employ robust methods to measure the metacognitive abilities of AI. This paper is primarily a methodological contribution that highlights a key limitation of commonly used measures of AI metacognitive sensitivity--the ability to generate confidence ratings that distinguish correct from incorrect responses. We then draw attention to the meta-d' framework, a well-established approach from psychology and neuroscience designed to address this limitation. Moreover, we propose to leverage signal detection theory (SDT) to measure the ability of AIs to spontaneously regulate their decisions based on uncertainty and risk. To demonstrate the practical utility of these psychophysical frameworks, we conduct two series of experiments on three large language models (LLMs)--GPT-5, DeepSeek-V3.2-Exp, and Mistral-Medium-2508.
Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系);Harbin Institute of Technology(哈尔滨工业大学);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院);School of Computer Science and Engineering, Central South University(中南大学计算机科学与工程学院)
School of Computer Science(计算机科学学院);Engineering, Sun Yat-sen University(工程,中山大学);School of Software Engineering(软件工程学院);Sun Yat-sen University(中山大学);Zhuhai Key Laboratory of Trusted Large Language Models(珠海可信大语言模型实验室);Tencent AI Lab(腾讯AI实验室);National University of Singapore(新加坡国立大学);Shenzhen University(深圳大学);Shanghai Jiao Tong University(上海交通大学)
ValueDCG: Measuring Comprehensive Human Value Understanding Ability of Language Models
Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);State Key Laboratory of General Artificial Intelligence, BIGAI(北京通用人工智能研究院通用人工智能国家重点实验室);School of Artificial Intelligence, Beijing University of Posts and Telecommunications(北京邮电大学人工智能学院)
The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors
NLP Department, Mohamed Bin Zayed University of Artificial Intelligence(马尔代夫比兹艾兹大学人工智能学院自然语言处理系);Ubiquitous Knowledge Processing Lab, Department of Computer Science(计算机科学系通用知识处理实验室);Hessian Center for AI (hessian.AI), TU Darmstadt(图尔努尔德马斯特大学海斯塞人工智能中心)
Measuring Outcomes in Healthcare Economics using Artificial Intelligence: with Application to Resource Management
George Mason University(乔治梅森大学);Virginia Polytechnic Institute and State University(弗吉尼亚理工学院暨州立大学);Brigham and Women’s Hospital, Harvard Medical School(哈佛医学院布莱根妇女医院)