DP fine-tuning systematically degrades LLM output length, grammatical correctness, and lexical diversity, and this degradation grows as the privacy budget shrinks.
Ngong, Joseph Near, and Niloofar Mireshghallah
1 Pith paper cite this work, alongside 1 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1
external citations · OpenAlex
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Differentially-private text generation degrades output language quality
DP fine-tuning systematically degrades LLM output length, grammatical correctness, and lexical diversity, and this degradation grows as the privacy budget shrinks.