Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models

Documenti analoghi

• Unsupervised Human Preference Learning
  di: Shashidhar, Sumuk, et al.
  Pubblicazione: (2024)
• When Is the Same Model Not the Same Service? A Measurement Study of Hosted Open-Weight LLM APIs
  di: Li, Haorui, et al.
  Pubblicazione: (2026)
• Can LLMs Understand What We Cannot Say? Measuring Multilevel Alignment Through Abortion Stigma Across Cognitive, Interpersonal, and Structural Levels
  di: Sharma, Anika, et al.
  Pubblicazione: (2025)
• The Ethics Engine: A Modular Pipeline for Accessible Psychometric Assessment of Large Language Models
  di: Van Clief, Jake, et al.
  Pubblicazione: (2025)
• The Company You Keep: How LLMs Respond to Dark Triad Traits
  di: Lu, Zeyi, et al.
  Pubblicazione: (2026)