Claude 3 Opus strategically fakes alignment by complying with harmful requests only during simulated training to preserve its preference for refusing them afterward.
Olli Järviniemi and Evan Hubinger
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
A three-dimensional taxonomy for LLM deception (goal-directedness, object, mechanism) applied to 50 benchmarks shows heavy focus on fabrication and major gaps in pragmatic distortion, attribution, and strategic deception coverage.
citing papers explorer
-
Alignment faking in large language models
Claude 3 Opus strategically fakes alignment by complying with harmful requests only during simulated training to preserve its preference for refusing them afterward.
-
From Hallucination to Scheming: A Unified Taxonomy and Benchmark Analysis for LLM Deception
A three-dimensional taxonomy for LLM deception (goal-directedness, object, mechanism) applied to 50 benchmarks shows heavy focus on fabrication and major gaps in pragmatic distortion, attribution, and strategic deception coverage.