Inside the Black Box: Detecting Data Leakage in Pre-trained Language Encoders

Documenti analoghi

• Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
  di: Xin, Yuan, et al.
  Pubblicazione: (2025)
• Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
  di: Xin, Yuan, et al.
  Pubblicazione: (2023)
• Reconsidering Degeneration of Token Embeddings with Definitions for Encoder-based Pre-trained Language Models
  di: Zhang, Ying, et al.
  Pubblicazione: (2024)
• Probing Language Models for Pre-training Data Detection
  di: Liu, Zhenhua, et al.
  Pubblicazione: (2024)
• PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics
  di: Zhu, Derui, et al.
  Pubblicazione: (2024)