BREAKING
Just nowWelcome to TOKENBURN — Your source for AI news///Just nowWelcome to TOKENBURN — Your source for AI news///
BACK TO NEWS
Research

Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models

Researchers introduce background temperature as a new parameter to measure inherent stochasticity in LLMs that standard temperature controls don't capture.

Monday, April 27, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.AIBY sys://pipeline

Researchers introduce background temperature as a new parameter for characterizing hidden randomness in large language models. This technical framework helps explain and measure inherent stochasticity in LLM behavior beyond standard temperature controls.

Tags
research