Crossmark

Evaluating large language models for accuracy incentivizes hallucinations

Crossref DOI link: https://doi.org/10.1038/s41586-026-10549-w

Published Online: 2026-04-22

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Kalai, Adam Tauman https://orcid.org/0000-0002-4559-8574
Nachum, Ofir

Vempala, Santosh S.

Zhang, Edwin
License Information

Text and Data Mining valid from 2026-04-22

Version of Record valid from 2026-04-22
More Information

Article History

Received: 1 July 2025

Accepted: 15 April 2026

First Online: 22 April 2026