Author

Devansh Srivastav

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Jan 2026

Unknown Unknowns: Do Hidden Intentions in LLMs Evade Detection?

This work introduces a social-science-grounded set of ten hidden intention categories and shows that they are trivially inducible, providing the first systematic analysis of why hidden intentions are difficult to detect.

Devansh Srivastav, D. Pape, Lea Schönherr · 1 citation