Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination

Documenti analoghi

• The Blessing of Dimensionality in LLM Fine-tuning: A Variance-Curvature Perspective
  di: Liang, Qiyao, et al.
  Pubblicazione: (2026)
• Do Diffusion Models Learn Semantically Meaningful and Efficient Representations?
  di: Liang, Qiyao, et al.
  Pubblicazione: (2024)
• Compositional Generalization via Forced Rendering of Disentangled Latents
  di: Liang, Qiyao, et al.
  Pubblicazione: (2025)
• Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space
  di: Qiu, Xin, et al.
  Pubblicazione: (2024)
• How Diffusion Models Learn to Factorize and Compose
  di: Liang, Qiyao, et al.
  Pubblicazione: (2024)