<!-- llms-explorer concept facts · https://llms-explorer.com/tree/consequences-for-tic-lists-and-detectors/ · pack 2026-09-23 · ~522 tokens -->

# Consequences for tic lists and detectors

> Source-anchored research for Consequences for tic lists and detectors. Run status: COMPLETED.

Parent: [Human adoption of LLM vocabulary and its effect on tic baselines](https://llms-explorer.com/tree/ai-isms-human-convergence/) · 3 facets · 6 facts · page: https://llms-explorer.com/tree/consequences-for-tic-lists-and-detectors/

## Measurements and reference values

- Enriching TOEFL essay vocabulary with ChatGPT cut the false positive rate from 61.22% to 11.77%, showing detectors key on vocabulary and predictability, not authorship. (medium confidence) — [source](https://arxiv.org/html/2304.02819)

## Comparisons and alternatives

- Seven GPT detectors misclassified non-native English TOEFL essays as AI with 61.22% average false positive rate, versus 5.19% on US 8th-grade essays; the mechanism is perplexity, since lower lexical variability reads as machine-like. (high confidence) — [source](https://arxiv.org/html/2304.02819)

## Facts and statements

- Wikipedia's Signs of AI writing guide says its signs indicate potential problems, not proof, that it is not a ban on words, and that treating signs as problems to fix could make detection harder. (low confidence) (verified as of 2026-09-23) — [source](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing)
- Tic vocabulary shifts by model generation (earlier delve/intricate, newer enhance/showcase), so a fixed word list decays and needs dating. (low confidence) (verified as of 2026-09-23) — [source](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing)
- A 2026 arXiv paper reports that writing style (vocabulary complexity, formality) is a confound causing detector false positives on academic writing, so formal human prose can be flagged. (low confidence) (verified as of 2026-08-28) — [source](https://arxiv.org/pdf/2608.26710)
- The Nigerian-English explanation for 'delve' is contested: comparing base Llama 2 to its RLHF-tuned version suggests RLHF preference itself promotes such words. (low confidence) — [source](https://arxiv.org/pdf/2412.11385)