Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Models

arXiv PDF
Read Paper Download PDF

Abstract

We evaluate how LLMs generate entropy and pseudorandom outputs in critical computational tasks, identifying key vulnerabilities and patterns.

Type Conference Paper
Venue KDD - Agentic & GenAI Evaluation 2025
Date Aug 2025
LLMs Randomness Entropy Security First Author