Related papers: How Robust are Model Rankings: A Leaderboard Custo…

As reinforcement learning (RL) achieves more success in solving complex tasks, more care is needed to ensure that RL research is reproducible and that algorithms herein can be compared easily and fairly with minimal bias. RL results are,…

The evaluation of supervised machine learning models is a critical stage in the development of reliable predictive systems. Despite the widespread availability of machine learning libraries and automated workflows, model assessment is often…

We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming honeypot evaluations take the form of coding tasks in Google's alignment research…

Textual adversarial attacks can discover models' weaknesses by adding semantic-preserved but misleading perturbations to the inputs. The long-lasting adversarial attack-and-defense arms race in Natural Language Processing (NLP) is…

If AI models can detect when they are being evaluated, the effectiveness of evaluations might be compromised. For example, models could have systematically different behavior during evaluations, leading to less reliable benchmarks for…

Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but their evaluations often collapse behavior into final task success. AgentAtlas reframes agent evaluation as a…

Benchmarks for the evaluation of model performance play an important role in machine learning. However, there is no established way to describe and create new benchmarks. What is more, the most common benchmarks use performance measures…

Fairness-aware learning aims to mitigate discrimination against specific protected social groups (e.g., those categorized by gender, ethnicity, age) while minimizing predictive performance loss. Despite efforts to improve fairness in…

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…

As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether…

As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…

Consider a scenario where we are supplied with a number of ready-to-use models trained on a certain source domain and hope to directly apply the most appropriate ones to different target domains based on the models' relative performance.…

In order to compare and benchmark the mathematical software, the performance profiles have been introduced [1]. However, it has been proved that the algorithm is not flawless. The main issue with the performance profile is that it may rank…

In the era of increasingly complex AI models for time series forecasting, progress is often measured by marginal improvements on benchmark leaderboards. However, this approach suffers from a fundamental flaw: standard evaluation metrics…

Algorithm evaluation and comparison are fundamental questions in machine learning and statistics -- how well does an algorithm perform at a given modeling task, and which algorithm performs best? Many methods have been developed to assess…

Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of their capabilities. Evaluating open-source LLMs through leaderboards faces persistent issues like data…

Public models offer predictions to a variety of downstream tasks and have played a crucial role in various AI applications, showcasing their proficiency in accurate predictions. However, the exclusive emphasis on prediction accuracy may not…

We introduce The FACTS Leaderboard, an online leaderboard suite and associated set of benchmarks that comprehensively evaluates the ability of language models to generate factually accurate text across diverse scenarios. The suite provides…

Imbalanced data poses a significant challenge in classification as model performance is affected by insufficient learning from minority classes. Balancing methods are often used to address this problem. However, such techniques can lead to…

With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching or even exceeding the human level on an increasing number of complex tasks. Impressive examples of this…