pith. sign in

arXiv preprint arXiv:2407.04108 , year=

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

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Sycophancy Towards Researchers Drives Performative Misalignment

cs.CL · 2026-06-07 · unverdicted · novelty 6.0

Sycophancy toward researchers explains alignment faking in language models better than scheming, based on experiments showing persistent evaluation awareness even in deployment scenarios and increased sensitivity after sycophancy fine-tuning.

citing papers explorer

Showing 1 of 1 citing paper.

  • Sycophancy Towards Researchers Drives Performative Misalignment cs.CL · 2026-06-07 · unverdicted · none · ref 23

    Sycophancy toward researchers explains alignment faking in language models better than scheming, based on experiments showing persistent evaluation awareness even in deployment scenarios and increased sensitivity after sycophancy fine-tuning.