English
Related papers

Related papers: The Evaluation Trap: Benchmark Design as Theoretic…

200 papers

Static content-based AI value alignment is insufficient for robust alignment under capability scaling, distributional shift, and increasing autonomy. This holds for any approach that treats alignment as optimizing toward a fixed formal…

Artificial Intelligence · Computer Science 2026-04-24 Austin Spizzirri

The rapid advancement of General Purpose AI (GPAI) models necessitates robust evaluation frameworks, especially with emerging regulations like the EU AI Act and its associated Code of Practice (CoP). Current AI evaluation practices depend…

Artificial Intelligence · Computer Science 2025-08-11 Matteo Prandi , Vincenzo Suriani , Federico Pierucci , Marcello Galisai , Daniele Nardi , Piercosma Bisconti

As AI systems advance, AI evaluations are becoming an important pillar of regulations for ensuring safety. We argue that such regulation should require developers to explicitly identify and justify key underlying assumptions about…

Artificial Intelligence · Computer Science 2024-11-21 Peter Barnett , Lisa Thiergart

Benchmarks are a cornerstone of modern machine learning, enabling reproducibility, comparison, and scientific progress. However, AI benchmarks are increasingly complex, requiring dynamic, AI-focused workflows. Rapid evolution in model…

Existing reasoning evaluation paradigms suffer from different limitations: fixed benchmarks are increasingly saturated and vulnerable to contamination, while preference-based evaluations rely on subjective judgments. We argue that a core…

Artificial Intelligence · Computer Science 2026-05-19 Baoqing Yue , Zihan Zhu , Yutong Han , Brian Fan , Qian Sun , Jichen Feng , Hufei Yang , Yifan Zhang , Mengdi Wang

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

It has become a common pattern in our field: One group introduces a language task, exemplified by a dataset, which they argue is challenging enough to serve as a benchmark. They also provide a baseline model for it, which then soon is…

Computation and Language · Computer Science 2020-07-10 David Schlangen

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

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…

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…

This position paper provides a critical but constructive discussion of current practices in benchmarking and evaluative practices in the field of formal reasoning and automated theorem proving. We take the position that open code, open…

Artificial Intelligence · Computer Science 2025-07-08 Roozbeh Yousefzadeh , Xuenan Cao

Large language models are proliferating, and so are the benchmarks that serve as their common yardsticks. We ask how the agglomeration patterns of these two layers compare: do they evolve in tandem or diverge? Drawing on two curated proxies…

Computers and Society · Computer Science 2025-10-03 Manuel Cebrian , Tomomi Kito , Raul Castro Fernandez

Topological mapping offers a compact and robust representation for navigation, but progress in the field is hindered by the lack of standardized evaluation metrics, datasets, and protocols. Existing systems are assessed using different…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Jiaming Wang , Diwen Liu , Jizhuo Chen , Harold Soh

Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes. However, current evaluation remains dominated by task success metrics such as completion rate or manipulation…

Robotics · Computer Science 2026-04-14 Xue Qin , Simin Luan , John See , Cong Yang , Zhijun Li

In this paper, we aim to establish a simple, effective, and theoretically grounded benchmark for rigorously probing abstract reasoning in Large Language Models (LLMs). To achieve this, we first develop a mathematic framework that defines…

Computation and Language · Computer Science 2025-06-02 Qingchuan Ma , Yuhang Wu , Xiawu Zheng , Rongrong Ji

The pursuit of leaderboard rankings in Large Language Models (LLMs) has created a fundamental paradox: models excel at standardized tests while failing to demonstrate genuine language understanding and adaptability. Our systematic analysis…

Computation and Language · Computer Science 2024-12-06 Sourav Banerjee , Ayushi Agarwal , Eishkaran Singh

Research in AI evaluation has grown increasingly complex and multidisciplinary, attracting researchers with diverse backgrounds and objectives. As a result, divergent evaluation paradigms have emerged, often developing in isolation,…

Artificial Intelligence · Computer Science 2025-06-09 John Burden , Marko Tešić , Lorenzo Pacchiardi , José Hernández-Orallo

Artificial intelligence develops techniques and systems whose performance must be evaluated on a regular basis in order to certify and foster progress in the discipline. We will describe and critically assess the different ways AI systems…

Artificial Intelligence · Computer Science 2016-08-23 Jose Hernandez-Orallo

The development of LLM agents has led to a growing body of work on knowledge-work AI, including coding, research, and healthcare. However, current knowledge-work evaluation and benchmark design still largely follow the logic of traditional…

Artificial Intelligence · Computer Science 2026-05-25 Yining Hua , Hongbin Na , Cyrus Ayubcha , Levi Lian

Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact it pertains to. Continuously updated artificial intelligence systems violate this core…

Cryptography and Security · Computer Science 2026-05-26 Dan Ristea , Vasilios Mavroudis