中文
相关论文

相关论文: Can We Trust AI Benchmarks? An Interdisciplinary R…

200 篇论文

AI safety benchmarks are pivotal for safety in advanced AI systems; however, they have significant technical, epistemic, and sociotechnical shortcomings. We present a review of 210 safety benchmarks that maps out common challenges in safety…

计算机与社会 · 计算机科学 2026-02-10 Cheng Yu , Severin Engelmann , Ruoxuan Cao , Dalia Ali , Orestis Papakyriakopoulos

AI models are increasingly prevalent in high-stakes environments, necessitating thorough assessment of their capabilities and risks. Benchmarks are popular for measuring these attributes and for comparing model performance, tracking…

人工智能 · 计算机科学 2024-11-21 Anka Reuel , Amelia Hardy , Chandler Smith , Max Lamparth , Malcolm Hardy , Mykel J. Kochenderfer

As artificial intelligence systems grow more powerful, there has been increasing interest in "AI safety" research to address emerging and future risks. However, the field of AI safety remains poorly defined and inconsistently measured,…

Artificial intelligence (AI) technologies (re-)shape modern life, driving innovation in a wide range of sectors. However, some AI systems have yielded unexpected or undesirable outcomes or have been used in questionable manners. As a…

Although AI systems are increasingly being leveraged to provide value to organizations, individuals, and society, significant attendant risks have been identified and have manifested. These risks have led to proposed regulations,…

人工智能 · 计算机科学 2024-12-06 David Piorkowski , Michael Hind , John Richards

The performance of AI models on safety benchmarks does not indicate their real-world performance after deployment. This opaqueness of AI models impedes existing regulatory frameworks constituted on benchmark performance, leaving them…

机器学习 · 计算机科学 2025-12-16 Gabriel Stanovsky , Renana Keydar , Gadi Perl , Eliya Habba

The number and importance of AI-based systems in all domains is growing. With the pervasive use and the dependence on AI-based systems, the quality of these systems becomes essential for their practical usage. However, quality assurance for…

软件工程 · 计算机科学 2023-08-02 Michael Felderer , Rudolf Ramler

Artificial Intelligence (AI) benchmarks play a central role in measuring progress in model development and guiding deployment decisions. However, many benchmarks quickly become saturated, meaning that they can no longer differentiate…

Artificial Intelligence (AI) technology epitomizes the complex challenges posed by human-made artifacts, particularly those widely integrated into society and exerting significant influence, highlighting potential benefits and their…

人工智能 · 计算机科学 2025-10-06 Michael Papademas , Xenia Ziouvelou , Antonis Troumpoukis , Vangelis Karkaletsis

AI models are increasingly deployed in live clinical environments where they must perform reliably across complex, high-stakes workflows that standard training and validation datasets were never designed to capture. Evaluating these systems…

人工智能 · 计算机科学 2026-05-12 Prasanna Desikan , Harshit Rajgarhia , Shivali Dalmia , Ananya Mantravadi

Building trust in AI-based systems is deemed critical for their adoption and appropriate use. Recent research has thus attempted to evaluate how various attributes of these systems affect user trust. However, limitations regarding the…

人机交互 · 计算机科学 2022-04-29 Michaela Benk , Suzanne Tolmeijer , Florian von Wangenheim , Andrea Ferrario

As frontier AI systems advance toward transformative capabilities, we need a parallel transformation in how we measure and evaluate these systems to ensure safety and inform governance. While benchmarks have been the primary method for…

人工智能 · 计算机科学 2025-05-12 Markov Grey , Charbel-Raphaël Segerie

The meteoric rise of AI, with its rapidly expanding market capitalization, presents both transformative opportunities and critical challenges. Chief among these is the urgent need for a new, unified paradigm for trustworthy evaluation, as…

Recent benchmark studies have claimed that AI has approached or even surpassed human-level performances on various cognitive tasks. However, this position paper argues that current AI evaluation paradigms are insufficient for assessing…

More than one hundred benchmarks have been developed to test the commonsense knowledge and commonsense reasoning abilities of artificial intelligence (AI) systems. However, these benchmarks are often flawed and many aspects of common sense…

人工智能 · 计算机科学 2023-02-24 Ernest Davis

Comprehensive and accurate evaluation of general-purpose AI systems such as large language models allows for effective mitigation of their risks and deepened understanding of their capabilities. Current evaluation methodology, mostly based…

人工智能 · 计算机科学 2024-01-01 Xiting Wang , Liming Jiang , Jose Hernandez-Orallo , David Stillwell , Luning Sun , Fang Luo , Xing Xie

The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges that undermine security evaluations: benchmark…

密码学与安全 · 计算机科学 2026-05-22 Sahar Abdelnabi , Chris Hicks , Konrad Rieck , Ahmad-Reza Sadeghi

Benchmarks are seen as the cornerstone for measuring technical progress in Artificial Intelligence (AI) research and have been developed for a variety of tasks ranging from question answering to facial recognition. An increasingly prominent…

计算机与社会 · 计算机科学 2022-04-12 Travis LaCroix , Alexandra Sasha Luccioni

AI evaluations are an important component of the AI governance toolkit, underlying current approaches to safety cases for preventing catastrophic risks. Our paper examines what these evaluations can and cannot tell us. Evaluations can…

计算机与社会 · 计算机科学 2024-12-13 Peter Barnett , Lisa Thiergart
‹ 上一页 1 2 3 10 下一页 ›