James H. Smith

Semantic Drift in Iterated LLM Paraphrase Chains: Model Architecture, Scale, Quantization, Serving Infrastructure, and Prompt Engineering

When large language models (LLMs) operate in sequential pipelines, each agent paraphrasing the output of the previous one, the cumulative signal diverges from the original in ways that are poorly understood. We study this semantic drift with a telephone-game protocol: a single te...