# Measuring convergence against pre-LLM baselines > Source-anchored research for Measuring convergence against pre-LLM baselines. Run status: COMPLETED. Parent: [Human adoption of LLM vocabulary and its effect on tic baselines](https://llms-explorer.com/tree/ai-isms-human-convergence/) · 4 facets · 6 facts · page: https://llms-explorer.com/tree/measuring-convergence-against-pre-llm-baselines/ ## How it works - Corpus check on the International Corpus of English found no evidence that focal words like delve are especially prevalent in any English variety, contradicting the Nigerian-English/RLHF-rater-origin explanation; RLHF itself remains a candidate cause. (medium confidence) — [source](https://arxiv.org/html/2412.11385v1) - A preregistered experiment (496 participants) showed brief chatbot interaction made people adopt its vocabulary, giving a causal mechanism beyond correlational baseline comparisons. (medium confidence) — [source](https://arxiv.org/abs/2409.01754) ## Measurements and reference values - Marker words are not stable baselines: per search summaries of the Yakura paper (v3), delve later declined below its pre-ChatGPT baseline in some categories (Science & Tech -15%, Education -11%, Business -30%), so a static pre-LLM frequency list can mislead. (low confidence) (verified as of 2026-09-23) — [source](https://arxiv.org/abs/2409.01754) ## Comparisons and alternatives - Kobak et al. measure LLM vocabulary influence as excess word frequency in 15M+ PubMed abstracts (2010-2024) versus pre-LLM years, an approach modelled on excess-mortality studies; they report a lower bound of at least 13.5% of 2024 abstracts LLM-processed, up to 40% in some subcorpora. (high confidence) — [source](https://arxiv.org/abs/2406.07016) - Yakura et al. use a synthetic-control method on 737,083 hours of podcast speech (824,634 episodes) plus YouTube academic talks: treated words like delve are compared with a weighted mix of donor words sharing pre-ChatGPT trends, and show an abrupt post-release rise. (high confidence) — [source](https://arxiv.org/abs/2409.01754) ## Facts and statements - Juzek and Ward take PubMed 2020 as the pre-LLM reference (LLMs not widespread before 2021), compare it with 2024, and define 21 focal words by three criteria: significant 2020-2024 rise, unexplained spike, and ChatGPT overuse relative to human abstracts. (medium confidence) — [source](https://arxiv.org/html/2412.11385v1)