# Researchers model how AI and humans time new words in text

Digest AI · Research · published 2026-10-14T04:00:00Z

Canonical: https://digestai.news/story/researchers-model-how-ai-and-humans-time-new-words-in-text

## Summary

A new paper on arXiv explores how information appears over time in natural language. The authors propose using neural temporal point processes to predict when new words or high-surprisal tokens appear in text sequences.

The study finds that AI models introduce new words at a much faster rate than humans, but both produce a decaying pattern of intensity over time for these events. However, high-surprisal tokens—words that are unexpected—do not show this difference between humans and AI. The findings challenge and expand earlier research, offering new insights into how language generation differs between humans and AI systems.

## Key points

- Researchers use neural temporal point processes to model timing of new words and high-surprisal tokens in text
- AI models generate new words faster than humans but share a decaying intensity pattern for both
- Study suggests AI and human language production differ in constrained context representation

## Why it matters

This work could refine how AI systems mimic human-like timing in text generation, improving naturalness and reducing unnatural bursts of new information.

## Sources

1. [Modeling the Arrival Time of Information-Bearing Events in Natural Language](https://arxiv.org/abs/2610.14212) (arXiv cs.CL, 2026-10-14, primary source)

## Cite

Digest AI, "Researchers model how AI and humans time new words in text", 14 October 2026, https://digestai.news/story/researchers-model-how-ai-and-humans-time-new-words-in-text

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-model-how-ai-and-humans-time-new-words-in-text.json