Related papers: General Scales Unlock AI Evaluation with Explanato…
Explainability in AI is gaining attention in the computer science community in response to the increasing success of deep learning and the important need of justifying how such systems make predictions in life-critical applications. The…
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…
AI models are increasingly deployed in live clinical environments where they must perform reliably across complex, high-stakes workflows that standard training and validation datasets were never designed to capture. Evaluating these systems…
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…
Developing safe and useful general-purpose AI systems will require us to make progress on scalable oversight: the problem of supervising systems that potentially outperform us on most skills relevant to the task at hand. Empirical work on…
Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities in reasoning, coding, and engineering tasks, it is…
Most AI benchmarks saturate within years or even months after they are introduced, making it hard to study long-run trends in AI capabilities. To address this challenge, we build a statistical framework that stitches benchmarks together,…
Benchmarks such as ARC, Raven-inspired tests, and the Blackbird Task are widely used to evaluate the intelligence of large language models (LLMs). Yet, the concept of intelligence remains elusive- lacking a stable definition and failing to…
Current AI alignment methodologies rely on human-provided demonstrations or judgments, and the learned capabilities of AI systems would be upper-bounded by human capabilities as a result. This raises a challenging research question: How can…
Data science is an integrated workflow of technical, analytical, communication, and ethical skills, but current AI benchmarks focus mostly on constituent parts. We test whether AI models can generate end-to-end data science projects. To do…
In recent years, Explainable AI (xAI) attracted a lot of attention as various countries turned explanations into a legal right. xAI allows for improving models beyond the accuracy metric by, e.g., debugging the learned pattern and…
Current evaluations of large language models (LLMs) rely on benchmark scores, but it is difficult to interpret what these individual scores reveal about a model's overall skills. Specifically, as a community we lack understanding of how…
Evaluation is no longer a final checkpoint in the machine learning lifecycle. As AI systems evolve from static models to compound, tool-using agents, evaluation becomes a core control function. The question is no longer "How good is the…
Advances in artificial intelligence need to become more resource-aware and sustainable. This requires clear assessment and reporting of energy efficiency trade-offs, like sacrificing fast running time for higher predictive performance.…
Benchmarks are pivotal in driving AI progress, and invalid benchmark questions frequently undermine their reliability. Manually identifying and correcting errors among thousands of benchmark questions is not only infeasible but also a…
Current Artificial Intelligence (AI) methods, most based on deep learning, have facilitated progress in several fields, including computer vision and natural language understanding. The progress of these AI methods is measured using…
AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging…
Large language models (LLMs) can internally distinguish between evaluation and deployment contexts, a behaviour known as \emph{evaluation awareness}. This undermines AI safety evaluations, as models may conceal dangerous capabilities during…
While the capabilities and utility of AI systems have advanced, rigorous norms for evaluating these systems have lagged. Grand claims, such as models achieving general reasoning capabilities, are supported with model performance on narrow…
In this paper, we offer a guide for researchers on evaluating reasoning in language models, building the case that reasoning should be assessed through evidence of adaptive, multi-step search rather than final-answer accuracy alone. Under…