B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability

Documenti analoghi

• Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?
  di: Wang, Yifan, et al.
  Pubblicazione: (2025)
• RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework
  di: Wang, Yifan, et al.
  Pubblicazione: (2024)
• Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization
  di: Liu, Dongqi, et al.
  Pubblicazione: (2023)
• PhoneLM:an Efficient and Capable Small Language Model Family through Principled Pre-training
  di: Yi, Rongjie, et al.
  Pubblicazione: (2024)
• Modeling Orthographic Variation Improves NLP Performance for Nigerian Pidgin
  di: Lin, Pin-Jie, et al.
  Pubblicazione: (2024)