Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens

Documenti analoghi

• MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector
  di: Fu, Wenjie, et al.
  Pubblicazione: (2024)
• Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
  di: Huo, Mingjia, et al.
  Pubblicazione: (2024)
• Machine Unlearning of Pre-trained Large Language Models
  di: Yao, Jin, et al.
  Pubblicazione: (2024)
• Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models
  di: Zhang, Tianchen, et al.
  Pubblicazione: (2024)
• Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens
  di: Salahuddin, Salahuddin, et al.
  Pubblicazione: (2025)