Pith. sign in

Benchmarks for detecting measurement tampering, 2023

Fabien Roger, Ryan Greenblatt, Max Nadeau, Buck Shlegeris, Nate Thomas · 2023 · arXiv 2308.15605

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
read on arXiv browse 1 citing papers

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

The Impossibility of Eliciting Latent Knowledge

cs.AI · 2026-06-10 · unverdicted · novelty 7.0

Proves that no behavior-dependent feedback training strategy can guarantee an honest agent for latent knowledge even with perfect training feedback.

citing papers explorer

Showing 1 of 1 citing paper.

  • The Impossibility of Eliciting Latent Knowledge cs.AI · 2026-06-10 · unverdicted · none · ref 32

    Proves that no behavior-dependent feedback training strategy can guarantee an honest agent for latent knowledge even with perfect training feedback.