ICML 2023 Workshop: Sampling and Optimization in Discrete Space, 4(1): 1–22

Can LLMs Generate Random Numbers? Evaluating LLM Sampling in Controlled Domains · 2023

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

browse 1 citing papers

representative citing papers

cs.LG · 2025-01-20 · conditional · novelty 5.0

GPT models asked to make random binary choices show large, version-specific biases; only GPT-4o-Mini came close to a 50/50 split in one-shot tests.

Showing 1 of 1 citing paper.

Evaluating Binary Decision Biases in Large Language Models: Implications for Fair Agent-Based Financial Simulations cs.LG · 2025-01-20 · conditional · none · ref 8
GPT models asked to make random binary choices show large, version-specific biases; only GPT-4o-Mini came close to a 50/50 split in one-shot tests.