Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs

Documenti analoghi

• Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
  di: Zhang, Qingru, et al.
  Pubblicazione: (2024)
• Learning a Decision Tree Algorithm with Transformers
  di: Zhuang, Yufan, et al.
  Pubblicazione: (2024)
• Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
  di: Chen, Yanda, et al.
  Pubblicazione: (2024)
• Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  di: Ge, Suyu, et al.
  Pubblicazione: (2023)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks
  di: Yu, Xiaodong, et al.
  Pubblicazione: (2023)