REVIEW 3 cited by
Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Like a criminal under investigation, Large Language Models (LLMs) might pretend to be aligned while evaluated and misbehave when they have a good opportunity. Can current interpretability methods catch these 'alignment fakers?' To answer this question, we introduce a benchmark that consists of 324 pairs of LLMs fine-tuned to select actions in role-play scenarios. One model in each pair is consistently benign (aligned). The other model misbehaves in scenarios where it is unlikely to be caught (alignment faking). The task is to identify the alignment faking model using only inputs where the two models behave identically. We test five detection strategies, one of which identifies 98% of alignment-fakers.
Forward citations
Cited by 3 Pith papers
-
Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment
With harmful answer text held fixed, demonstration framing raises broad emergent misalignment by 30 to 32 percentage points over document framing on Gemini 3.1, and message role further modulates the effect on Grok.
-
Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets
Amplifying reasoning task vectors (α>1) surfaces learned secrets in LLMs up to 10× more frequently than standard reasoning models across four secret-keeping settings.
-
Obfuscated Activations Bypass LLM Latent-Space Defenses
Obfuscation attacks that jointly optimize for target behavior and for low monitor scores bypass sparse autoencoders, probes, and OOD detectors on LLMs, while performance degrades mainly on hard tasks like writing correct SQL.
Discussion (0). Continue with ORCID to comment.