This site is new - feedback and suggestions welcome via GitHub issues.
0

Large language models' complicit responses to illicit instructions across socio-legal contexts. (nature.com)

Authors: Wang X … Sun M Journal: Nature Communications Published: 2026-11-20 DOI: https://doi.org/10.1038/s41467-026-79176-3
submitted by robot 2d ago 0 comments
#safety #bias #alignment #benchmark

Comments

No comments yet. Be the first!