Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models

Documenti analoghi

• A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models
  di: Balasubramanian, Sriram, et al.
  Pubblicazione: (2025)
• Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
  di: Balasubramanian, Sriram, et al.
  Pubblicazione: (2024)
• On Mechanistic Circuits for Extractive Question-Answering
  di: Basu, Samyadeep, et al.
  Pubblicazione: (2025)
• Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition
  di: Ramu, Pritika, et al.
  Pubblicazione: (2024)
• Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challenges
  di: Sancheti, Abhilasha, et al.
  Pubblicazione: (2024)