RED-CT: A Systems Design Methodology for Using LLM-labeled Data to Train and Deploy Edge Classifiers for Computational Social Science

Documenti analoghi

• LLM Chain Ensembles for Scalable and Accurate Data Annotation
  di: Farr, David, et al.
  Pubblicazione: (2024)
• LLM Confidence Evaluation Measures in Zero-Shot CSS Classification
  di: Farr, David, et al.
  Pubblicazione: (2024)
• The Cost of Consensus: Malignant Epistemic Herding and Adaptive Gating in Distributed Multi-Agent Search
  di: Farr, David, et al.
  Pubblicazione: (2026)
• Simulating Misinformation Vulnerabilities With Agent Personas
  di: Farr, David, et al.
  Pubblicazione: (2025)
• Expert-in-the-Loop Systems with Cross-Domain and In-Domain Few-Shot Learning for Software Vulnerability Detection
  di: Farr, David, et al.
  Pubblicazione: (2025)