본문으로 건너뛰기

Juhyeon's Blog

태그: calibration

7건의 항목

  • 2026년 6월 04일

    Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations

    • paper
    • LLM
    • hallucination
    • calibration
    • representation-engineering
    • verbal-uncertainty
    • inference-time-intervention
    • linear-feature
    • theory
  • 2026년 6월 04일

    Cognitive Dissonance - Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness

    • paper/theory
    • LLM
    • interpretability
    • truthfulness
    • probing
    • calibration
    • deception
    • safety
    • EMNLP2024
  • 2026년 6월 04일

    Epistemic AI is Essential for ML Models to Truly Know When They Dont Know

    • paper/theory
    • uncertainty
    • epistemic-ai
    • credal-set
    • random-set
    • dempster-shafer
    • OOD
    • calibration
    • self-knowledge
    • imprecise-probability
  • 2026년 6월 04일

    On Verbalized Confidence Scores for LLMs

    • llm
    • uncertainty-quantification
    • calibration
    • verbalized-confidence
    • prompting
    • self-knowledge
    • metacognition
    • trustworthy-ai
    • black-box-uq
    • benchmark
  • 2026년 6월 04일

    Teaching LLMs to Abstain across Languages via Multilingual Feedback

    • multilingual
    • abstention
    • LLM-safety
    • fairness
    • calibration
    • cross-lingual
    • EMNLP2024
    • knowledge-boundary
    • self-reflection
    • training
  • 2026년 6월 04일

    Thinking Faithful and Stable - Mitigating Hallucinations in LLMs via Internal Consistency

    • LLM
    • hallucination
    • faithfulness
    • self-consistency
    • calibration
    • RLHF
    • reasoning
    • uncertainty
    • theory
    • arxiv-2511-15921
  • 2026년 6월 04일

    Uncertainty-Based Abstention in LLMs Improves Safety

    • paper
    • LLM
    • uncertainty
    • abstention
    • safety
    • hallucination
    • calibration
    • selective-prediction
    • trustworthy-AI
    • metacognition
    • training

키보드 단축키

/ 또는 Ctrl+K검색
?단축키 도움말
Esc모달 닫기

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Blog