Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation

Documenti analoghi

• Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution
  di: Sinha, Ankita, et al.
  Pubblicazione: (2024)
• Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models
  di: Zhang, Jiaxin, et al.
  Pubblicazione: (2024)
• Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
  di: Chuang, Yung-Sung, et al.
  Pubblicazione: (2024)
• The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs
  di: Baidya, Avinash, et al.
  Pubblicazione: (2025)
• Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
  di: Huang, Yanwen, et al.
  Pubblicazione: (2025)