Feature-Aware Malicious Output Detection and Mitigation

Documenti analoghi

• LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation
  di: Wang, Keheng, et al.
  Pubblicazione: (2024)
• Rectify Evaluation Preference: Improving LLMs' Critique on Math Reasoning via Perplexity-aware Reinforcement Learning
  di: Tian, Changyuan, et al.
  Pubblicazione: (2025)
• Latent Distribution Decoupling: A Probabilistic Framework for Uncertainty-Aware Multimodal Emotion Recognition
  di: Huang, Jingwang, et al.
  Pubblicazione: (2025)
• IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
  di: Shi, Dan, et al.
  Pubblicazione: (2024)
• Localizing Malicious Outputs from CodeLLM
  di: Borana, Mayukh, et al.
  Pubblicazione: (2025)