← authors · overview

• Estimating Knowledge In Large Language Models Without Generating A Single Token
  2024 · 36 citations
• Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers
  2024 · 6 citations
• From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty
  2024 · 2 citations
• Estimating Knowledge in Large Language Models Without Generating a Single Token
  2024 · 2 citations
• Enhancing Automated Interpretability with Output-Centric Feature Descriptions
  2025 · 1 citations
• Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
  2026
• Hallucinations Undermine Trust; Metacognition is a Way Forward
  2026
• Friends and Grandmothers in Silico: Localizing Entity Cells in Language Models
  2026
• Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
  2026
• Latent Reasoning With Supervised Thinking States
  2026
• Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization