English
Related papers

Related papers: The Evaluation Differential: When Frontier AI Mode…

200 papers

Representational distinctions within categories are important in all perceptual modalities and also in cognitive and motor representations. Recent pattern-information studies of brain activity have used condition-rich designs to sample the…

Neurons and Cognition · Quantitative Biology 2022-05-20 Hamed Nili , Alexander Walther , Arjen Alink , Nikolaus Kriegeskorte

Current AI-driven educational systems primarily rely on behavioural analytics, performance metrics, and content-level interactions to model learning. While these approaches provide useful indicators of learner activity, they are…

Human-Computer Interaction · Computer Science 2026-05-19 Annie Yuan

AI governance frameworks increasingly rely on audits, yet the results of their underlying evaluations require interpretation and context to be meaningfully informative. Even technically rigorous evaluations can offer little useful insight…

Computers and Society · Computer Science 2025-08-18 Leon Staufer , Mick Yang , Anka Reuel , Stephen Casper

Large language models (LLMs) can use in-context demonstrations to improve performance on zero-shot tasks. However, selecting the best in-context examples is challenging because model performance can vary widely depending on the selected…

Computation and Language · Computer Science 2023-11-29 Dan Iter , Reid Pryzant , Ruochen Xu , Shuohang Wang , Yang Liu , Yichong Xu , Chenguang Zhu

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…

Artificial Intelligence · Computer Science 2026-05-12 Miles Q. Li , Benjamin C. M. Fung , Martin Weiss , Pulei Xiong , Khalil Al-Hussaeni , Claude Fachkha

As artificial intelligence (AI) models are scaled up, new capabilities can emerge unintentionally and unpredictably, some of which might be dangerous. In response, dangerous capabilities evaluations have emerged as a new risk assessment…

Computers and Society · Computer Science 2023-10-03 Jide Alaga , Jonas Schuett

Despite the enormous performance of deepneural networks (DNNs), recent studies have shown theirvulnerability to adversarial examples (AEs), i.e., care-fully perturbed inputs designed to fool the targetedDNN. Currently, the literature is…

Computer Vision and Pattern Recognition · Computer Science 2021-07-14 Anouar Kherchouche , Sid Ahmed Fezza , Wassim Hamidouche

Recent work has suggested post-hoc explainers might be ineffective for detecting spurious correlations in Deep Neural Networks (DNNs). However, we show there are serious weaknesses with the existing evaluation frameworks for this setting.…

Machine Learning · Computer Science 2022-11-16 Shea Cardozo , Gabriel Islas Montero , Dmitry Kazhdan , Botty Dimanov , Maleakhi Wijaya , Mateja Jamnik , Pietro Lio

Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge. One promising solution is Unsupervised Environment Design (UED), a co-evolutionary framework in which a teacher adaptively generates…

Machine Learning · Computer Science 2026-03-17 Geonwoo Cho , Jaegyun Im , Jihwan Lee , Hojun Yi , Sejin Kim , Sundong Kim

Two key identifying assumptions used to justify difference-in-differences are parallel trends and no anticipation, yet both may fail in practice. I propose a class of assumptions on anticipation and derive closed-form, sharp bounds on the…

Econometrics · Economics 2026-03-03 Gianna Fenaroli

Recent AI media detectors report near-perfect performance under clean laboratory evaluation, yet their robustness under realistic deployment conditions remains underexplored. In practice, AI-generated images are resized, compressed,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Aishwarya Budhkar , Trishita Dhara , Siddhesh Sheth

Reinforcement learning (RL) in non-stationary environments is challenging, as changing dynamics and rewards quickly make past experiences outdated. Traditional experience replay (ER) methods, especially those using TD-error prioritization,…

Machine Learning · Computer Science 2025-09-19 Tianyang Duan , Zongyuan Zhang , Songxiao Guo , Yuanye Zhao , Zheng Lin , Zihan Fang , Yi Liu , Dianxin Luan , Dong Huang , Heming Cui , Yong Cui

AI agents execute complex multi-step processes, but current evaluation falls short: outcome metrics report success or failure without explaining why, and process-level approaches struggle to connect failure types to their precise locations…

Anomaly Detection (AD) defines the task of identifying observations or events that deviate from typical - or normal - patterns, a critical capability in IT security for recognizing incidents such as system misconfigurations, malware…

AI integration in automotive perception systems shifts requirements from static specifications to continuously evolving entities shaped by data, models, and operating contexts. When such changes are not consistently documented, validated,…

Software Engineering · Computer Science 2026-05-01 Hina Saeeda , Soniya Abraham

Backdoor attacks on language models pose a significant threat to AI safety, where models behave normally on most inputs but exhibit harmful behavior when triggered by specific patterns. Detecting such backdoors through mechanistic…

Computation and Language · Computer Science 2026-05-11 Sachin Kumar

The performance of speech emotion recognition is affected by the differences in data distributions between train (source domain) and test (target domain) sets used to build and evaluate the models. This is a common problem, as multiple…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-15 Mohammed Abdelwahab , Carlos Busso

The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…

Cryptography and Security · Computer Science 2026-04-28 Richard Joseph Mitchell

Differences-in-differences (DiD) is a causal inference method for observational longitudinal data that assumes parallel expected potential outcome trajectories between treatment groups under the counterfactual scenario where all units…

Methodology · Statistics 2026-05-12 Michael Jetsupphasuk , Didong Li , Michael G. Hudgens

A key challenge in computer vision and deep learning is the definition of robust strategies for the detection of adversarial examples. Here, we propose the adoption of ensemble approaches to leverage the effectiveness of multiple detectors…

Computer Vision and Pattern Recognition · Computer Science 2022-02-16 Francesco Craighero , Fabrizio Angaroni , Fabio Stella , Chiara Damiani , Marco Antoniotti , Alex Graudenzi