TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods

Documenti analoghi

• Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization
  di: Loiseau, Gabriel, et al.
  Pubblicazione: (2026)
• Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization
  di: Loiseau, Gabriel, et al.
  Pubblicazione: (2025)
• Distilling Human-Aligned Privacy Sensitivity Assessment from Large Language Models
  di: Loiseau, Gabriel, et al.
  Pubblicazione: (2026)
• Attention Overflow: Language Model Input Blur during Long-Context Missing Items Recommendation
  di: Sileo, Damien
  Pubblicazione: (2024)
• Logic Haystacks: Probing LLMs Long-Context Logical Reasoning (Without Easily Identifiable Unrelated Padding)
  di: Sileo, Damien
  Pubblicazione: (2025)