PRISM forms predictions as sparse mixtures of learned prototypes trained with clustering objectives, matching dense model accuracy while enabling ~500x faster data attribution and behavior editing without finetuning.
Generalized group data attribution, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Prototype Language Models
PRISM forms predictions as sparse mixtures of learned prototypes trained with clustering objectives, matching dense model accuracy while enabling ~500x faster data attribution and behavior editing without finetuning.