The maximum reward gain under KL-regularized LM alignment is a Jeffreys divergence term, estimable as covariance from base samples, with best-of-N approaching the theoretical limit.
Ai deception: A survey of examples, risks, and potential solutions.Patterns, 5(5)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
DECOR introduces a theory-grounded multi-agent system that decomposes contexts into atomic units, scores four manipulation dimensions per unit, and aggregates profiles into a global deception index, reporting SOTA results on single- and multi-turn benchmarks.
citing papers explorer
-
Theoretical Limits of Language Model Alignment
The maximum reward gain under KL-regularized LM alignment is a Jeffreys divergence term, estimable as covariance from base samples, with best-of-N approaching the theoretical limit.
-
DECOR: Auditing LLM Deception via Information Manipulation Theory
DECOR introduces a theory-grounded multi-agent system that decomposes contexts into atomic units, scores four manipulation dimensions per unit, and aggregates profiles into a global deception index, reporting SOTA results on single- and multi-turn benchmarks.