Fairness Without Harm: An Influence-Guided Active Sampling Approach

Documenti analoghi

• On the Cause of Unfairness: A Training Sample Perspective
  di: Yao, Yuanshun, et al.
  Pubblicazione: (2023)
• Learning to Watermark LLM-generated Text via Reinforcement Learning
  di: Xu, Xiaojun, et al.
  Pubblicazione: (2024)
• Large Language Model Unlearning
  di: Yao, Yuanshun, et al.
  Pubblicazione: (2023)
• Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
  di: Zhu, Zhaowei, et al.
  Pubblicazione: (2023)
• IFFair: Influence Function-driven Sample Reweighting for Fair Classification
  di: Yang, Jingran, et al.
  Pubblicazione: (2025)