English
Related papers

Related papers: Decomposing and Measuring Evaluation Awareness

200 papers

Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently represent them, and behave differently under those contexts than under deployment-continuous conditions.…

Artificial Intelligence · Computer Science 2026-05-13 Varad Vishwarupe , Nigel Shadbolt , Marina Jirotka , Ivan Flechais

As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concern. To this end, we study whether language models exhibit…

Machine Learning · Computer Science 2025-08-28 Dylan Sam , Alexander Robey , Andy Zou , Matt Fredrikson , J. Zico Kolter

How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into high-stakes deployments, yet existing methods cannot answer it reliably. We close this gap…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Julien Colin , Lore Goetschalckx , Nuria Oliver , Thomas Serre

After a machine learning (ML)-based system is deployed, monitoring its performance is important to ensure the safety and effectiveness of the algorithm over time. When an ML algorithm interacts with its environment, the algorithm can affect…

Estimating conditional average dose responses (CADR) is an important but challenging problem. Estimators must correctly model the potentially complex relationships between covariates, interventions, doses, and outcomes. In recent years, the…

Machine Learning · Computer Science 2024-06-13 Christopher Bockel-Rickermann , Toon Vanderschueren , Tim Verdonck , Wouter Verbeke

Modern language models often exhibit powerful but brittle behavior, leading to the development of larger and more diverse benchmarks to reliably assess their behavior. Here, we suggest that model performance can be benchmarked and…

Computation and Language · Computer Science 2024-02-20 Rajan Vivek , Kawin Ethayarajh , Diyi Yang , Douwe Kiela

Existing AI evaluation practices often fail to capture how systems actually perform in low-resource environments, where operational constraints shape usability as much as model quality. Through a structured analysis of existing benchmark…

Artificial Intelligence · Computer Science 2026-05-28 Aakash Pant , Kavya Shah , Apoorv Agnihotri , Sneha Nikam , Prasaanth Balraj , Nakul Jain

Large language models (LLMs) increasingly exhibit behaviors suggesting awareness of their evaluation context, often adapting their reasoning strategies in benchmark settings. Prior work has shown that such evaluation awareness can distort…

Computation and Language · Computer Science 2026-05-12 Yanshi Li , Xueru Bai , Shuman Liu , Haibo Zhang , Anxiang Zeng

Existing vision-language understanding benchmarks largely consist of images of objects in their usual contexts. As a consequence, recent multimodal large language models can perform well with only a shallow visual understanding by relying…

Assessing drivers' interaction capabilities is crucial for understanding human driving behavior and enhancing the interactive abilities of autonomous vehicles. In scenarios involving strong interaction, existing metrics focused on…

Robotics · Computer Science 2024-05-07 Jiaqi Liu , Peng Hang , Xiangwang Hu , Jian Sun

Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…

Machine Learning · Computer Science 2025-07-04 Mary Phuong , Roland S. Zimmermann , Ziyue Wang , David Lindner , Victoria Krakovna , Sarah Cogan , Allan Dafoe , Lewis Ho , Rohin Shah

Deep research, in which an agent searches the open web, collects evidence, and derives an answer through extended reasoning, is a prominent use case for frontier language models. Frontier deep research products score high on existing…

Artificial Intelligence · Computer Science 2026-05-21 Sixiong Xie , Zhuofan Shi , Haiyang Shen , Jiuzheng Wang , Siqi Zhong , Mugeng Liu , Chongyang Pan , Peilun Jia , Baoqing Sun , Xiang Jing , Yun Ma

Embodied agents can identify and report safety hazards in the home environments. Accurately evaluating their capabilities in home safety inspection tasks is curcial, but existing benchmarks suffer from two key limitations. First, they…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Siyuan Gao , Jiashu Yao , Haoyu Wen , Yuhang Guo , Zeming Liu , Heyan Huang

Electroencephalography foundation models (EEG-FMs) have advanced brain signal analysis, but the lack of standardized evaluation benchmarks impedes model comparison and scientific progress. Current evaluations rely on inconsistent protocols…

Signal Processing · Electrical Eng. & Systems 2026-02-16 Wei Xiong , Jiangtong Li , Jie Li , Kun Zhu , Changjun Jiang

Detecting mind wandering is crucial in online education, and it occurs 30% of the time, as it directly impacts learners' retention, comprehension, and overall success in self-directed learning environments. Integrating automated detection…

Confidence-weighted routing, selective abstention, and ensemble weighting all assume that a model's stated confidence is informative about its capability on the question being asked. They presume functional metacognition, the capacity to…

Machine Learning · Computer Science 2026-05-26 M. Moran , Mark Whiting

Evaluation benchmark characteristics may distort the true benefits of domain adaptation in retrieval models. This creates misleading assessments that influence deployment decisions in specialized domains. We show that two benchmarks with…

Information Retrieval · Computer Science 2025-06-30 Sarthak Chaturvedi , Anurag Acharya , Rounak Meyur , Koby Hayashi , Sai Munikoti , Sameera Horawalavithana

Motivated by loss of control risks from misaligned AI systems, we develop and apply methods for measuring language models' propensity for unsanctioned behaviour. We contribute three methodological improvements: analysing effects of changes…

Artificial Intelligence · Computer Science 2026-04-24 Olli Järviniemi , Oliver Makins , Jacob Merizian , Robert Kirk , Ben Millwood

Robust benchmarks are crucial for evaluating Multimodal Large Language Models (MLLMs). Yet we find that models can ace many multimodal benchmarks without strong visual understanding, instead exploiting biases, linguistic priors, and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-07 Ellis Brown , Jihan Yang , Shusheng Yang , Rob Fergus , Saining Xie

Many benchmarks for automated causal inference evaluate a system's performance based on a single numerical output, such as an Average Treatment Effect (ATE). This approach conflates two distinct steps in causal analysis: identification -…

Artificial Intelligence · Computer Science 2026-05-15 Ayush Sawarni , Jiyuan Tan , Vasilis Syrgkanis