Heterogeneity in Formal Linguistic Competence of Language Models: Is Data the Real Bottleneck?

Documenti analoghi

• SMART: Submodular Data Mixture Strategy for Instruction Tuning
  di: Renduchintala, H S V N S Kowndinya, et al.
  Pubblicazione: (2024)
• POSIX: A Prompt Sensitivity Index For Large Language Models
  di: Chatterjee, Anwoy, et al.
  Pubblicazione: (2024)
• On the Effect of Instruction Tuning Loss on Generalization
  di: Chatterjee, Anwoy, et al.
  Pubblicazione: (2025)
• Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying
  di: Renduchintala, Adithya, et al.
  Pubblicazione: (2023)
• Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases
  di: Hu, Michael Y., et al.
  Pubblicazione: (2025)