English
Related papers

Related papers: Deprecating Benchmarks: Criteria and Framework

200 papers

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,…

Benchmarks are crucial to measuring and steering progress in artificial intelligence (AI). However, recent studies raised concerns over the state of AI benchmarking, reporting issues such as benchmark overfitting, benchmark saturation and…

Artificial Intelligence · Computer Science 2022-12-13 Simon Ott , Adriano Barbosa-Silva , Kathrin Blagec , Jan Brauner , Matthias Samwald

Commonly, AI or machine learning (ML) models are evaluated on benchmark datasets. This practice supports innovative methodological research, but benchmark performance can be poorly correlated with performance in real-world applications -- a…

Machine Learning · Computer Science 2024-06-18 Olivier Binette , Jerome P. Reiter

Benchmarking has long served as a foundational practice in machine learning and, increasingly, in modern AI systems such as large language models, where shared tasks, metrics, and leaderboards offer a common basis for measuring progress and…

Artificial Intelligence · Computer Science 2026-02-16 Philip Waggoner

The creation of benchmarks to evaluate the safety of Large Language Models is one of the key activities within the trusted AI community. These benchmarks allow models to be compared for different aspects of safety such as toxicity, bias,…

Artificial Intelligence · Computer Science 2025-06-23 Lina Berrayana , Sean Rooney , Luis Garcés-Erice , Ioana Giurgiu

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…

Computers and Society · Computer Science 2022-04-12 Travis LaCroix , Alexandra Sasha Luccioni

Evaluation of reasoning language models gained importance after it was observed that they can combine their existing capabilities into novel traces of intermediate steps before task completion and that the traces can sometimes help them to…

Machine Learning · Computer Science 2025-08-15 Petr Spelda , Vit Stritecky

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…

Artificial Intelligence · Computer Science 2023-02-24 Ernest Davis

Following the AI Seoul Summit in 2024, twelve AI companies published frontier AI safety frameworks (Frameworks) outlining their approaches to managing catastrophic risks from advanced AI systems. Emerging legislation increasingly treats…

Computers and Society · Computer Science 2026-05-01 Lily Stelling , Malcolm Murray , Bruno Galizzi , Max Schaffelder , Siméon Campos , Henry Papadatos

Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However, current AI safety…

Existing AI benchmarks for software automation rarely combine cross-application coordination, autonomous API discovery, and policy adherence. Real business workflows demand all three: a single task may span a CRM, inbox, calendar, and…

Artificial Intelligence · Computer Science 2026-04-22 Daniel Shepard , Robin Salimans

Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results. Yet the field studies it without a shared foundation, conflating properties of the evaluation…

Machine Learning · Computer Science 2026-05-25 Changling Li , Terry Jingchen Zhang , Jie Zhang , Zhijing Jin , Sahar Abdelnabi , Maksym Andriushchenko

Reinforcement learning has recently experienced increased prominence in the machine learning community. There are many approaches to solving reinforcement learning problems with new techniques developed constantly. When solving problems…

Machine Learning · Computer Science 2020-12-14 Belinda Stapelberg , Katherine M. Malan

Benchmarking, standards and certification are closely related processes. Standards can provide normative requirements that robotics and AI systems may or may not conform to. Certification generally relies upon conformance with one or more…

Robotics · Computer Science 2023-09-22 Alan F. T. Winfield , Matthew Studley

Cultural AI benchmarks often rely on implicit assumptions about measured constructs, leading to vague formulations with poor validity and unclear interrelations. We propose exposing these assumptions using explicit cognitive models…

Artificial Intelligence · Computer Science 2024-09-26 Jonathan H. Rystrøm , Kenneth C. Enevoldsen

The rapid adoption of AI agents across domains has made systematic evaluation crucial for ensuring their usefulness and successful production deployment. Evaluation of AI agents typically involves using a fixed set of benchmarks and…

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…

Cryptography and Security · Computer Science 2026-05-22 Sahar Abdelnabi , Chris Hicks , Konrad Rieck , Ahmad-Reza Sadeghi

A `state of the art' model A surpasses humans in a benchmark B, but fails on similar benchmarks C, D, and E. What does B have that the other benchmarks do not? Recent research provides the answer: spurious bias. However, developing A to…

Computation and Language · Computer Science 2020-08-11 Swaroop Mishra , Anjana Arunkumar , Bhavdeep Sachdeva , Chris Bryan , Chitta Baral

Ensuring safe and effective use of AI requires understanding and anticipating its performance on novel tasks, from advanced scientific challenges to transformed workplace activities. So far, benchmarking has guided progress in AI, but it…

AI-driven program repair uses AI models to repair buggy software by producing patches. Rapid advancements in AI surely impact state-of-the-art performance of program repair. Yet, grasping this progress requires frequent and standardized…

Software Engineering · Computer Science 2025-10-28 André Silva , Martin Monperrus