A causal audit of LMLMs finds near-zero parametric leakage after deletion, with surviving correctness coming from retrieval artifacts in the database.
Title resolution pending
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
-
Auditing Forgetting in Limited Memory Language Models
A causal audit of LMLMs finds near-zero parametric leakage after deletion, with surviving correctness coming from retrieval artifacts in the database.