arXiv AI September 7, 2026 By Nathan Wolfrath, Meghan Conroy, Thomas Kosten, Dave Bell, Bhabishya Neupane, Jonah Kindel, Anjishnu Banerjee, Priya Deshpande, Bradley Taylor, Anai N. Kothari

Model Retirement Creates Reproducibility Risk in Biomedical AI Publications

Read the original on arXiv AI →

The study examined biomedical research articles from 2022 to March 2026 that employed large language models (LLMs). It found that 42% of the most frequently used models were already retired or scheduled to retire within two years of publication, with a median retirement interval of 538 days. This high rate of model deprecation threatens the reproducibility of biomedical AI research.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 28

The Half-Lives of Generative-AI Evidence: A 40-Record Audit, a Claim-Currency Framework, and a Reflexive Case of Frontier-Model-Assisted Research

arXiv:2607. 24032v1 Announce Type: new Abstract: Generative-AI evaluations can become historical before publication, yet calendar age does not affect every conclusion equally.

By Carlo Iacono (Charles Sturt University, Australia)

llms

Hugging Face Trending Papers

Jul 27

The Half-Lives of Generative-AI Evidence: A 40-Record Audit, a Claim-Currency Framework, and a Reflexive Case of Frontier-Model-Assisted Research

Generative-AI evaluations can become historical before publication, yet calendar age does not affect every conclusion equally. This paper has two linked purposes.

llms

arXiv Computation and Language

Sep 11

The widening evaluation gap in medical large language model research 2023 to 2026

The article examines how medical research lags behind the rapid evolution of large language models (LLMs). From January 2023 to June 2026, PubMed records in fourteen clinical domains grew 45‑fold, yet only 2.5 % employed randomized, controlled, or prospective designs. The evaluation gap widened from 1.33 to 6.08 quarters, with randomized trials assessing models that were on average 4.6 quarters older than other studies, and 62 % of such trials evaluated discontinued model families.

By Raad Bin Tareaf, Murad Al-Rajab, Samia Loucif

llms

arXiv AI

Jul 2

Continuous Knowledge Metabolism: Generating Scientific Hypotheses from Evolving Literature

arXiv:2604. 12243v2 Announce Type: replace-cross Abstract: Identifying promising research directions in fast-moving subareas is one of the most cognitively expensive tasks in modern AI research.

By Jinkai Tao, Yubo Wang, Xiaoyu Liu, Menglin Yang

llms agents benchmarks

arXiv Computation and Language

Sep 15

Biomedical Reference Generation Remains Unreliable across 26 Large Language Models

arXiv:2609.14988v1 Announce Type: new Abstract: Background. Large language models are increasingly used to help write biomedical text but may fabricate references to nonexistent work. How often large...

By Maxim Topaz, Zhihong Zhang, Nir Roguin, Pallavi Gupta, Zichao Li, Laura-Maria Peltonen

llms

arXiv Machine Learning

Jun 2

The Ghost Couple: Correlated LLM Name Priors and Their Haunting of the Web and Academic Publishing

arXiv:2606. 02184v1 Announce Type: cross Abstract: These names do not exist.

By Micha{\l} Brzozowski, Neo Christopher Chung

llms

One email a morning, machine-written

Related stories

The Half-Lives of Generative-AI Evidence: A 40-Record Audit, a Claim-Currency Framework, and a Reflexive Case of Frontier-Model-Assisted Research

The Half-Lives of Generative-AI Evidence: A 40-Record Audit, a Claim-Currency Framework, and a Reflexive Case of Frontier-Model-Assisted Research

The widening evaluation gap in medical large language model research 2023 to 2026

Continuous Knowledge Metabolism: Generating Scientific Hypotheses from Evolving Literature

Biomedical Reference Generation Remains Unreliable across 26 Large Language Models

The Ghost Couple: Correlated LLM Name Priors and Their Haunting of the Web and Academic Publishing