Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models

Documenti analoghi

• LLM Review: Enhancing Creative Writing via Blind Peer Review Feedback
  di: Li, Weiyue, et al.
  Pubblicazione: (2026)
• Post-hoc Reward Calibration: A Case Study on Length Bias
  di: Huang, Zeyu, et al.
  Pubblicazione: (2024)
• BiasFilter: An Inference-Time Debiasing Framework for Large Language Models
  di: Cheng, Xiaoqing, et al.
  Pubblicazione: (2025)
• Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models
  di: Hao, Teqi, et al.
  Pubblicazione: (2025)
• Rethinking Prompt-based Debiasing in Large Language Models
  di: Yang, Xinyi, et al.
  Pubblicazione: (2025)