An 8B local language model, trained with an adversarial self-play workflow and reinforcement learning, anonymizes user-generated text with 12.3% better privacy protection and 6.8% better utility than prior LLM-based anonymizers on two synthetic datasets.
Aligning llms with individual preferences via interaction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text
An 8B local language model, trained with an adversarial self-play workflow and reinforcement learning, anonymizes user-generated text with 12.3% better privacy protection and 6.8% better utility than prior LLM-based anonymizers on two synthetic datasets.