English

AI Benchmarks and Datasets for LLM Evaluation

Distributed, Parallel, and Cluster Computing 2024-12-03 v1 Artificial Intelligence

Abstract

LLMs demand significant computational resources for both pre-training and fine-tuning, requiring distributed computing capabilities due to their large model sizes \cite{sastry2024computing}. Their complex architecture poses challenges throughout the entire AI lifecycle, from data collection to deployment and monitoring \cite{OECD_AIlifecycle}. Addressing critical AI system challenges, such as explainability, corrigibility, interpretability, and hallucination, necessitates a systematic methodology and rigorous benchmarking \cite{guldimann2024complai}. To effectively improve AI systems, we must precisely identify systemic vulnerabilities through quantitative evaluation, bolstering system trustworthiness. The enactment of the EU AI Act \cite{EUAIAct} by the European Parliament on March 13, 2024, establishing the first comprehensive EU-wide requirements for the development, deployment, and use of AI systems, further underscores the importance of tools and methodologies such as Z-Inspection. It highlights the need to enrich this methodology with practical benchmarks to effectively address the technical challenges posed by AI systems. To this end, we have launched a project that is part of the AI Safety Bulgaria initiatives \cite{AI_Safety_Bulgaria}, aimed at collecting and categorizing AI benchmarks. This will enable practitioners to identify and utilize these benchmarks throughout the AI system lifecycle.

Keywords

Cite

@article{arxiv.2412.01020,
  title  = {AI Benchmarks and Datasets for LLM Evaluation},
  author = {Todor Ivanov and Valeri Penchev},
  journal= {arXiv preprint arXiv:2412.01020},
  year   = {2024}
}

Comments

November 2024 v1.0

R2 v1 2026-06-28T20:18:56.298Z