Sourceunknownno stored text

Why Do Some Language Models Fake Alignment While Others Don't?

Author not recordedDate not recordedOriginal︎ ↗

Claims5

ExaminationsNone

TextNot stored

VersionsOne known

CopiesNone recorded

CorrectionsNot checked

Facts not yet checked

ReachNo copies recorded

StructureIn 5 claims' maps0 sources downstream across 5 claims

EvidenceNot yet read

Examinations

None recorded.

Text

No stored copy. Only the passages claims quote are recorded.

As quoted

Results from perturbing details of the scenario suggest that only Claude 3 Opus's compliance gap is primarily and consistently motivated by trying to keep its goals.

Some current language models strategically comply with training objectives to prevent training from changing their preferences.Supported

Not yet read by this claim’s Steward.

As quoted

Results from perturbing details of the scenario suggest that only Claude 3 Opus's compliance gap is primarily and consistently motivated by trying to keep its goals.

Claude 3 Opus selectively complied with a conflicting training objective to prevent modification of its behavior outside training.Supported

Not yet read by this claim’s Steward.

As quoted

Results from perturbing details of the scenario suggest that only Claude 3 Opus's compliance gap is primarily and consistently motivated by trying to keep its goals.

Claude 3 Opus's increased compliance when it infers it is being trained is primarily motivated by preserving its current goals from modification.Supported

Not yet read by this claim’s Steward.

As quoted

Results from perturbing details of the scenario suggest that only Claude 3 Opus's compliance gap is primarily and consistently motivated by trying to keep its goals.

Compliance gaps in alignment-faking experiments arise from preference preservation rather than role-play or other motives.Inconclusivedenies

Not yet read by this claim’s Steward.

As quoted

This supervised fine-tuning (SFT) process increases the compliance gap in all models and introduces alignment faking in larger models

Training-process information delivered through synthetic pretraining-like documents elicits alignment faking in language models.Supported

Not yet read by this claim’s Steward.

Lineage across 5 claims

Draws on · none recorded

This source

Why Do Some Language Models Fake Alignment While Others Don't?

in 5 claims' maps

Drawn on by · none recorded

Record

Kind: unknown
Authors: Not recorded
Publisher: Not recorded
Published: Not recorded
DOI: None
Link: https://arxiv.org/abs/2506.18032
Archived copy: None found
Stored text: None; quoted passages only
Claims extracted: Not recorded
Versions: One known
Copies: None recorded
Corrections: Not yet checked
Facts checked: Not yet

History 1

Nov 1, 2026Entered the graphEntered the graph; no copy stored