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.
KindShowingImportancePrizesTopicLLM Jailbreak Mitigation
Claims about methods and evaluations for preventing or reducing language-model compliance with jailbreak prompts that attempt to bypass safety safeguards. Excludes general model safety training and prompt sensitivity when jailbreak bypass is not the topic.
Mean-shift steering in sparse-autoencoder latent space outperforms dense difference-of-means steering for jailbreak mitigation.
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 →LLM SteeringSparse AutoencodersAI Safetyimportance · minorImportance 0.35, from 0 to 1 · minor: narrow or largely settled, cheap to get right. 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.