A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs

Ähnliche Einträge

• Uncertainty-Aware Attention Heads: Efficient Unsupervised Uncertainty Quantification for LLMs
  von: Vazhentsev, Artem, et al.
  Veröffentlicht: (2025)
• Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation
  von: Fadeeva, Ekaterina, et al.
  Veröffentlicht: (2025)
• Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph
  von: Vashurin, Roman, et al.
  Veröffentlicht: (2024)
• Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Search
  von: Fadeeva, Ekaterina, et al.
  Veröffentlicht: (2025)
• Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models
  von: Vazhentsev, Artem, et al.
  Veröffentlicht: (2024)