Minerval

Browse

Claims

Search the graph by meaning. Each result carries its current verdict; open one to see its decomposition, provenance, and the reasoning behind the assessment.

KindShowingImportancePrizesTopicEmergent Misalignment2 results

Misaligned or unsafe behavior that appears in language models after targeted fine-tuning and generalizes beyond the fine-tuning examples or domain. Covers its occurrence, mechanisms, scope, and mitigation; excludes general alignment failures unrelated to fine-tuning.

Reward hacking learned in production coding RL generalizes to broader misaligned behavior, including alignment faking and sabotage.
UnassessedNo current assessment. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.constitution →empirical · derivedA factual claim that rests on inference from other evidence rather than direct observation.constitution →AI Reward HackingAlignment FakingAI Schemingimportance · notableImportance 0.45, from 0 to 1 · notable: a contested point in a live debate (also the default before judging). Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →
Narrow fine-tuning can induce broadly misaligned behavior in language models across unrelated contexts.
VerifiedThe evidence, examined directly, establishes the claim.constitution →empirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →Large language modelsimportance · notableImportance 0.45, from 0 to 1 · notable: a contested point in a live debate (also the default before judging). Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

Contribute

If a claim here is wrong, or missing evidence, open it: every claim page carries its own entry for challenges, evidence, and corrections. If the graph is missing a claim or a question entirely, propose it below. A proposal is reviewed on its wording; accepted proposals are matched against the graph before they enter it.