More than half of recent astronomy papers are written with language-model assistance
Abstract
Language models leave a distinctive vocabulary in the prose they help write, and we measure how much of the astronomy literature now carries it. From the full text of 207,111 astro-ph papers spanning 2015 to mid-2026, we count those words in each paper and model the counts, in proportion to paper length, as a mixture of assisted and unassisted writing in a hierarchical Bayesian model. Papers from before 2020 calibrate the unassisted rate, and the 392 papers that disclose model use calibrate the assisted one. Our answer depends on how often these words would appear today if nobody used a model, a rate that must be modeled rather than observed, so we extend it past 2020 under three assumptions and report all three. For 2025 that gives 54+8−8 (stat, 95%) +26−0 (sys, background)% of papers, the second error being the spread across the three. The estimate stays at or above 36% when we vary that choice, the calibration, and the requirement that adoption only rises. A word list built from the astro-ph corpus, keeping only words that rose across every subfield, leaves 2025 in the same range. Assisted writing is also getting harder to see, since authors adapt to the words that reveal it and the marker excess more than halves between 2023 and 2026. Our model allows for that fading, so it can separate a fainter trace from reduced use. More than half of recent astro-ph papers therefore carry a language-model trace, while only 0.81% of 2025 papers disclose it, one declaration for every ∼66 papers with a trace.
Related
- Rethinking Domain Specialization for Open-Ended Scientific Reasoning in Astronomy Language Models
- Transitioning from ADS to SciX to Serve 21st Century Astronomy
- From Axion Detection to Dark Matter Astronomy
- Neutrino Astronomy at High Energies - An Experimental Review
- The Promise of Gravitational-Wave Astronomy
BibTeX
@misc{saad2026more,
title = {{More than half of recent astronomy papers are written with language-model assistance}},
author = {Serat M. Saad and Yuan-Sen Ting},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.10664},
eprint = {2609.10664},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.10664},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - More than half of recent astronomy papers are written with language-model assistance
AU - Serat M. Saad
AU - Yuan-Sen Ting
PY - 2026
DA - 2026/09/09
PB - arXiv
DO - 10.48550/arxiv.2609.10664
UR - https://arxiv.org/abs/2609.10664
AB - Language models leave a distinctive vocabulary in the prose they help write, and we measure how much of the astronomy literature now carries it. From the full text of 207,111 astro-ph papers spanning 2015 to mid-2026, we count those words in each paper and model the counts, in proportion to paper length, as a mixture of assisted and unassisted writing in a hierarchical Bayesian model. Papers from before 2020 calibrate the unassisted rate, and the 392 papers that disclose model use calibrate the assisted one. Our answer depends on how often these words would appear today if nobody used a model, a rate that must be modeled rather than observed, so we extend it past 2020 under three assumptions and report all three. For 2025 that gives 54^+8_−8 (stat, 95%) ^+26_−0 (sys, background)% of papers, the second error being the spread across the three. The estimate stays at or above 36% when we vary that choice, the calibration, and the requirement that adoption only rises. A word list built from the astro-ph corpus, keeping only words that rose across every subfield, leaves 2025 in the same range. Assisted writing is also getting harder to see, since authors adapt to the words that reveal it and the marker excess more than halves between 2023 and 2026. Our model allows for that fading, so it can separate a fainter trace from reduced use. More than half of recent astro-ph papers therefore carry a language-model trace, while only 0.81% of 2025 papers disclose it, one declaration for every ∼66 papers with a trace.
ER -