Deterministic or probabilistic? The psychology of LLMs as random number generators

TL;DR

This paper investigates whether large language models produce truly random numbers or exhibit deterministic patterns due to training biases, revealing that their randomness is often predictable and influenced by model architecture and prompt language.

Contribution

The study systematically analyzes LLMs' ability to generate random numbers, highlighting deterministic tendencies and biases rooted in training data that affect their randomness.

Findings

LLMs often produce deterministic responses when asked for random numbers.

Model architecture and prompt language significantly influence the randomness of outputs.

Training data biases lead to predictable patterns, undermining genuine randomness.

Abstract

Large Language Models (LLMs) have transformed text generation through inherently probabilistic context-aware mechanisms, mimicking human natural language. In this paper, we systematically investigate the performance of various LLMs when generating random numbers, considering diverse configurations such as different model architectures, numerical ranges, temperature, and prompt languages. Our results reveal that, despite their stochastic transformers-based architecture, these models often exhibit deterministic responses when prompted for random numerical outputs. In particular, we find significant differences when changing the model, as well as the prompt language, attributing this phenomenon to biases deeply embedded within the training data. Models such as DeepSeek-R1 can shed some light on the internal reasoning process of LLMs, despite arriving to similar results. These biases induce predictable patterns that undermine genuine randomness, as LLMs are nothing but reproducing our own human cognitive biases.