Controlled Text Generation for Black-box Language Models via Score-based Progressive Editor

Documenti analoghi

• A Multifaceted Analysis of Negative Bias in Large Language Models through the Lens of Parametric Knowledge
  di: Song, Jongyoon, et al.
  Pubblicazione: (2025)
• Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination
  di: Song, Jongyoon, et al.
  Pubblicazione: (2024)
• EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models
  di: Lee, Che Hyun, et al.
  Pubblicazione: (2025)
• Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context
  di: Yu, Sangwon, et al.
  Pubblicazione: (2024)
• Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment
  di: Yu, Sangwon, et al.
  Pubblicazione: (2024)