The 8088 The 8088 ← All news
arXiv cs.AI AI Research Apr 27

Large Language Models Are Bad Dice Players: LLMs Struggle to Generate Random Numbers from Statistical Distributions

★★★★★ significance 3/5

Researchers conducted a large-scale audit revealing that large language models struggle significantly to generate random numbers from specific statistical distributions. The study found that while batch generation shows modest success, independent requests almost entirely fail to meet statistical requirements, leading to systematic biases in downstream tasks.

Why it matters Systematic failures in statistical randomness undermine the reliability of LLMs for stochastic modeling and downstream algorithmic decision-making.
Read the original at arXiv cs.AI

Tags

#llm #probabilistic sampling #statistical bias #stochasticity #benchmark

Related coverage