# Trailing participial analysis phrases > Source-anchored research for Trailing participial analysis phrases. Run status: COMPLETED. Parent: [LLM rhetorical-pattern tells in prose](https://llms-explorer.com/tree/ai-isms-rhetorical-tells/) · 3 facets · 6 facts · page: https://llms-explorer.com/tree/trailing-participial-analysis-phrases/ ## How it works - Watch-list participles named by the Wikipedia guide: highlighting/underscoring/emphasizing, reflecting/symbolizing, contributing to, cultivating/fostering, enhancing. It treats the tell as stronger when the verb's subject is an inanimate fact or event. (low confidence) (verified as of 2026-09-23) — [source](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) ## Comparisons and alternatives - Reinhart et al. (CMU/NJIT, arXiv 2410.16107, Oct 2024) found instruction-tuned models use present participial clauses at 2-5x the human rate: GPT-4o 527%, GPT-4o Mini 481%, Llama 3 70B Instruct 261%, 8B Instruct 224%, versus base models near human levels (94-102%). (low confidence) — [source](https://arxiv.org/html/2410.16107v1) ## Facts and statements - Wikipedia's Signs of AI writing guide says chatbots attach a present-participle (-ing) phrase at sentence end to add superficial analysis of significance, recognition or impact, sometimes with vague attributions; on Wikipedia such comments are usually synthesis or unattributed opinion. (medium confidence) (verified as of 2026-09-23) — [source](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) - Base Llama 3 models show human-like participial rates, so the excess is introduced by instruction tuning, not pretraining. (low confidence) — [source](https://arxiv.org/html/2410.16107v1) - The pattern is only a potential sign, not proof: the Wikipedia guide says such patterns also occur in human writing (editorials, fan fiction) and human style is increasingly influenced by LLMs. (medium confidence) — [source](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) - Stylometric detectors relying on surface features show high false positives and poor domain transfer (Pudasaini et al., arXiv 2603.23146), so a participial-phrase count alone should not be used to accuse text of being AI-written. (low confidence) (verified as of 2026-09-23) — [source](https://arxiv.org/pdf/2603.23146)