Entity-level membership inference determines whether information about a target real-world entity was used in LLM training, using only black-box generated text and achieving AUC up to 0.97 on person entities.
Investigative interviewing witness guide flashcards,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Have You Ever Seen Them? Entity-level Membership Inference through Interrogating Large Language Models
Entity-level membership inference determines whether information about a target real-world entity was used in LLM training, using only black-box generated text and achieving AUC up to 0.97 on person entities.