A production mobile-keyboard error-correction system that synthesizes large LLM-generated training data, reweights it with a differentially private federated small LM, and fine-tunes a billion-parameter LLM via LoRA reports 2.47-7.18% relative A/B metric gains.
(amplified) banded matrix factorization: A unified approach to private training
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Synthesizing and Adapting Error Correction Data for Mobile Large Language Model Applications
A production mobile-keyboard error-correction system that synthesizes large LLM-generated training data, reweights it with a differentially private federated small LM, and fine-tunes a billion-parameter LLM via LoRA reports 2.47-7.18% relative A/B metric gains.