Confidence-Aware Routing for Large Language Model Reliability Enhancement: A Multi-Signal Approach to Pre-Generation Hallucination Mitigation

Documenti analoghi

• DeepRAG: Building a Custom Hindi Embedding Model for Retrieval Augmented Generation from Scratch
  di: M, Nandakishor
  Pubblicazione: (2025)
• I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation
  di: Zong, Haotian, et al.
  Pubblicazione: (2026)
• MALM: A Multi-Information Adapter for Large Language Models to Mitigate Hallucination
  di: Jia, Ao, et al.
  Pubblicazione: (2025)
• An Evolutionary Large Language Model for Hallucination Mitigation
  di: Boulesnane, Abdennour, et al.
  Pubblicazione: (2024)
• Credal Transformer: A Principled Approach for Quantifying and Mitigating Hallucinations in Large Language Models
  di: Ji, Shihao, et al.
  Pubblicazione: (2025)