Can Small-Scale Data Poisoning Exacerbate Dialect-Linked Biases in Large Language Models?

Documenti analoghi

• Obscuring Data Contamination Through Translation: Evidence from Arabic Corpora
  di: Abbas, Chaymaa, et al.
  Pubblicazione: (2026)
• On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models
  di: Sahili, Ali Al, et al.
  Pubblicazione: (2025)
• Relative Value Biases in Large Language Models
  di: Hayes, William M., et al.
  Pubblicazione: (2024)
• Large Language Models are Biased Reinforcement Learners
  di: Hayes, William M., et al.
  Pubblicazione: (2024)
• PARAMANU-GANITA: Can Small Math Language Models Rival with Large Language Models on Mathematical Reasoning?
  di: Niyogi, Mitodru, et al.
  Pubblicazione: (2024)