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

Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models

★★★★★ significance 3/5

Researchers introduce the concept of 'background temperature' to explain why large language models produce divergent outputs even when temperature is set to zero. The paper identifies implementation-level sources of non-determinism, such as floating-point non-associativity and kernel non-invariance, and proposes a protocol to estimate this effect.

Why it matters Uncovering hardware-level sources of non-determinism challenges the reliability of zero-temperature sampling and the fundamental predictability of LLM outputs.
Read the original at arXiv cs.AI

Tags

#llm #determinism #inference #reproducibility #stochasticity

Related coverage