The Text Uncanny Valley: Non-Monotonic Performance Degradation in LLM Information Retrieval

Documenti analoghi

• Linearly Decoding Refused Knowledge in Aligned Language Models
  di: Shrivastava, Aryan, et al.
  Pubblicazione: (2025)
• Know Thyself? On the Incapability and Implications of AI Self-Recognition
  di: Bai, Xiaoyan, et al.
  Pubblicazione: (2025)
• Moral Mazes in the Era of LLMs
  di: Nguyen, Dang, et al.
  Pubblicazione: (2026)
• The Story is Not the Science: Execution-Grounded Evaluation of Mechanistic Interpretability Research
  di: Bai, Xiaoyan, et al.
  Pubblicazione: (2026)
• LLM Probability Concentration: How Alignment Shrinks the Generative Horizon
  di: Yang, Chenghao, et al.
  Pubblicazione: (2025)