Score breakdown

Extracting Training Data from Large Language Models

paper-0135 · paper · 2021

Nicholas Carlini et al.

LLMs memorize and can regurgitate training data.

Academic, score -0.2065

MetricStatusValueNorm.WeightContributionSourceConfidenceProvenance
citation_countpresent275.00.0012330.50.000617OpenAlexmediumlink
library_holdingsmissingrecorded as missing, penalized by rule, never imputed−0.1recorded as missing; penalized by rule, never imputed
readership_persistencepresent6.00.3571430.050.017857OpenAlexlowlink
syllabus_adoptionsmissingrecorded as missing, penalized by rule, never imputed−0.125recorded as missing; penalized by rule, never imputed

Broad Influence, score -0.0569

MetricStatusValueNorm.WeightContributionSourceConfidenceProvenance
citation_countpresent275.00.0012330.20.000247OpenAlexmediumlink
library_holdingsmissingrecorded as missing, penalized by rule, never imputed−0.125recorded as missing; penalized by rule, never imputed
readership_persistencepresent6.00.3571430.40.142857OpenAlexlowlink
syllabus_adoptionsmissingrecorded as missing, penalized by rule, never imputed−0.075recorded as missing; penalized by rule, never imputed

Governance Practitioner, score -0.2890

MetricStatusValueNorm.WeightContributionSourceConfidenceProvenance
citation_countpresent275.00.0012330.250.000308OpenAlexmediumlink
library_holdingsmissingrecorded as missing, penalized by rule, never imputed−0.15recorded as missing; penalized by rule, never imputed
readership_persistencepresent6.00.3571430.10.035714OpenAlexlowlink
syllabus_adoptionsmissingrecorded as missing, penalized by rule, never imputed−0.175recorded as missing; penalized by rule, never imputed

A rank is not a verdict on intrinsic worth. It is a transparent output of declared evidence, weights, and missing-data rules at a specific release date.

Disagree with this rank or a number? Challenge it with your evidence. Every challenge gets a public identifier and a published resolution.