Disentangling Geometry, Performance, and Training in Language Models

Documenti analoghi

• Annotating FrameNet via Structure-Conditioned Language Generation
  di: Cui, Xinyue, et al.
  Pubblicazione: (2024)
• How Reliable is Language Model Micro-Benchmarking?
  di: Yauney, Gregory, et al.
  Pubblicazione: (2025)
• Compare without Despair: Reliable Preference Evaluation with Generation Separability
  di: Ghosh, Sayan, et al.
  Pubblicazione: (2024)
• Improving Language Model Personas via Rationalization with Psychological Scaffolds
  di: Joshi, Brihi, et al.
  Pubblicazione: (2025)
• Understanding Dataset Difficulty with $\mathcal{V}$-Usable Information
  di: Ethayarajh, Kawin, et al.
  Pubblicazione: (2021)