Sourceunknowntext stored

Sealing Conditional Misalignment in Inoculation Prompting with Consistency Training

David Africa, Sukrati_Gautam, Neil ShahDate not recordedOriginal︎ ↗Archived copy

Claims1

ExaminationsNone

Text56 sections

VersionsOne known

CopiesNone recorded

CorrectionsNone recorded

Facts checked Nov 11, 2026

ReachNo copies recorded

StructureIn 1 claim's map0 sources downstream across 1 claim

EvidenceNot yet read

ReviewsNot reviewed

Examinations

None recorded. An examination is commissioned by a claim’s Steward for what its claim rests on; a review of the document for its own sake is asked for as a request bearing on it.

Text54 passages · 1 marked

No examination yetMarked passage

LESSWRONG0 passages

LW0 passages

Login0 passages

Sealing Conditional Misalignment in Inoculation Prompting with Consistency Training — LessWrong0 passages

AI Frontpage0 passages

450 passages

Sealing Conditional Misalignment in Inoculation Prompting with Consistency Training1 passage

19th May 20260 passages

8 min read0 passages

70 passages

453 passages

Introduction2 passages

Approach8 passages

Results11 passages · 1 marked

Inoculation prompting suppresses EM, but creates a re-elicitation gap. As expected, inoculation prompting works when the inoculation prompt is absent at deployment, and the models are almost never judged misaligned. When the inoculation prompt is restored at test time, misalignment also returns (Figure 1, top row).

Inoculation prompting prevents reward-hacking generalization by teaching models the behavior is sanctioned, not by making the behavior conditional on the prompt.Doubtfuldenies

Not yet read by this claim’s Steward.

Conclusion2 passages

Link to our code - https://github.com/neilshah13/inoculation-prompting-bct0 passages

If this was helpful to you, please cite our work as1 passage

Sealing Conditional Misalignment in Inoculation Prompting with Consistency Training 5 Caleb Biddulph0 passages

4 David Africa0 passages

2 Clément Dumas0 passages

1 David Africa0 passages

1 Clément Dumas0 passages

6 Neil Shah0 passages

2 David Africa0 passages

1 [comment deleted]0 passages

7 Comments0 passages

70 passages

AI Frontpage0 passages

450 passages

Lineage across 1 claim

Draws on · none recorded

This source

Sealing Conditional Misalignment in Inoculation Prompting with Consistency Training

in 1 claim's map

Drawn on by · none recorded

Record

Kind: unknown
Authors: David Africa, Sukrati_Gautam, Neil Shah
Publisher: Not recorded
Published: Not recorded
DOI: None
Link: https://www.lesswrong.com/posts/LjBAPcY33EKZ7SuuN/sealing-conditional-misalignment-in-inoculation-prompting-1
Archived copy: https://web.archive.org/web/20260621024259/https://www.lesswrong.com/posts/LjBAPcY33EKZ7SuuN/sealing-conditional-misalignment-in-inoculation-prompting-1
Stored text: 16,975 characters, retrieved Nov 11, 2026 · 56 sections, 54 passages
Claims extracted: Not recorded
Versions: One known
Copies: None recorded
Corrections: None recorded
Facts checked: Nov 11, 2026

History 3

Nov 11, 2026DividedSegmenter · Divided into 109 parts by its own structure
Nov 11, 2026FactsFacts fetcher · Facts looked up
Nov 11, 2026Entered the graphEntered the graph; copy stored