CIP: A Plug-and-Play Causal Prompting Framework for Mitigating Hallucinations under Long-Context Noise

Documenti analoghi

• Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation
  di: Wang, Dianyun, et al.
  Pubblicazione: (2025)
• ESG-Bench: Benchmarking Long-Context ESG Reports for Hallucination Mitigation
  di: Sun, Siqi, et al.
  Pubblicazione: (2026)
• Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation
  di: Ajwani, Rohan Deepak, et al.
  Pubblicazione: (2024)
• S$^3$-Attention:Attention-Aligned Endogenous Retrieval for Memory-Bounded Long-Context Inference
  di: Ma, Qingsen, et al.
  Pubblicazione: (2026)
• Towards Long Context Hallucination Detection
  di: Liu, Siyi, et al.
  Pubblicazione: (2025)