相关论文: Fantastic Bugs and Where to Find Them in AI Benchm…

Quantitative Artificial Intelligence (AI) Benchmarks have emerged as fundamental tools for evaluating the performance, capability, and safety of AI models and systems. Currently, they shape the direction of AI development and are playing an…

AI models are increasingly prevalent in high-stakes environments, necessitating thorough assessment of their capabilities and risks. Benchmarks are popular for measuring these attributes and for comparing model performance, tracking…

The rapid adoption of AI agents across domains has made systematic evaluation crucial for ensuring their usefulness and successful production deployment. Evaluation of AI agents typically involves using a fixed set of benchmarks and…

Autonomous AI research agents aim to accelerate scientific discovery by automating the research pipeline, from hypothesis generation to peer review. However, existing benchmarks rarely test a fundamental bottleneck: whether Large Language…

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…

The rapid rise in popularity of Large Language Models (LLMs) with emerging capabilities has spurred public curiosity to evaluate and compare different LLMs, leading many researchers to propose their own LLM benchmarks. Noticing preliminary…

Large language model (LLM) evaluation is increasingly costly, prompting interest in methods that speed up evaluation by shrinking benchmark datasets. Benchmark prediction (also called efficient LLM evaluation) aims to select a small subset…

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…

AI safety benchmarks are pivotal for safety in advanced AI systems; however, they have significant technical, epistemic, and sociotechnical shortcomings. We present a review of 210 safety benchmarks that maps out common challenges in safety…

Benchmarks are essential for unified evaluation and reproducibility. The rapid rise of Artificial Intelligence for Software Engineering (AI4SE) has produced numerous benchmarks for tasks such as code generation and bug repair. However, this…

As frontier artificial intelligence (AI) models rapidly advance, benchmarks are integral to comparing different models and measuring their progress in different task-specific domains. However, there is a lack of guidance on when and how…

The rapid adoption of Large Language Models (LLMs) has spurred interest in automated peer review; however, progress is currently stifled by benchmarks that treat reviewing primarily as a rating prediction task. We argue that the utility of…

We introduce a benchmark framework developed by and for the scientific community to evaluate, monitor and steer large language model development in fundamental physics. Building on philosophical concepts of scientific understanding and…

There is a tendency across different subfields in AI to valorize a small collection of influential benchmarks. These benchmarks operate as stand-ins for a range of anointed common problems that are frequently framed as foundational…

Benchmarks are the de facto standard for tracking progress in large language models (LLMs), yet static test sets can rapidly saturate, become vulnerable to contamination, and are costly to refresh. Scalable evaluation of open-ended items…

Effective financial reasoning demands not only textual understanding but also the ability to interpret complex visual data such as charts, tables, and trend graphs. This paper introduces a new benchmark designed to evaluate how well AI…

Benchmarking optimization algorithms is fundamental for the advancement of computational intelligence. However, widely adopted artificial test suites exhibit limited correspondence with the diversity and complexity of real-world engineering…

The rapid proliferation of benchmarks for evaluating large language models (LLMs) has created an urgent need for systematic methods to assess benchmark quality itself. We propose Benchmark^2, a comprehensive framework comprising three…

As AI systems are increasingly used to conduct research autonomously, misaligned systems could introduce subtle flaws that produce misleading results while evading detection. We introduce Auditing Sabotage Bench, a benchmark for evaluating…

Evaluation for many natural language understanding (NLU) tasks is broken: Unreliable and biased systems score so highly on standard benchmarks that there is little room for researchers who develop better systems to demonstrate their…