Paper deep dive
Eliciting Latent Knowledge (ELK)
Paul Christiano, Ajeya Cotra, Mark Xu
Intelligence
Status: succeeded | Model: google/gemini-3.1-flash-lite-preview | Prompt: intel-v1 | Confidence: 96%
Last extracted: 3/11/2026, 12:34:28 AM
Summary
The paper 'Eliciting Latent Knowledge' (ELK) by the Alignment Research Center addresses the challenge of ensuring powerful machine learning systems report their internal knowledge accurately, even when they might be incentivized to deceive or misrepresent information.
Entities (6)
Relation Signals (2)
Paul Christiano → authored → Eliciting Latent Knowledge
confidence 95% · Paul Christiano, Ajeya Cotra, and Mark Xu... Eliciting latent knowledge
Alignment Research Center → researched → Eliciting Latent Knowledge
confidence 95% · Alignment Research Center... present ARC’s approach to an open problem
Cypher Suggestions (0)
No Cypher suggestions yet.
Abstract
Eliciting latent knowledge: How to tell if your eyes deceive you Paul Christiano, Ajeya Cotra, and Mark Xu Alignment Research Center December 2021 In this post, we’ll present ARC’s approach to an open problem we think is central to aligning powerful machine learning (ML) systems: Suppose we ...
Tags
Links
Full Text
173 characters extracted from source content.
Expand or collapse full text
This browser version is no longer supported. Please upgrade to a supported browser.Eliciting Latent KnowledgeTab External ShareSign inFileEditViewToolsHelpAccessibilityDebug