← authors · overview

• Estimating Knowledge In Large Language Models Without Generating A Single Token
  2024 · 36 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
• Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
  2026
• Hallucinations Undermine Trust; Metacognition is a Way Forward
  2026
• Latent Reasoning With Supervised Thinking States
  2026
• Universal Jailbreak Suffixes Are Strong Attention Hijackers
  2025
• Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization
  2025
• Universal Jailbreak Suffixes Are Strong Attention Hijackers
  2025
• LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations
  2025
• Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
  2025
• The Hidden Language of Diffusion Models
  2023
• In-Context Learning Creates Task Vectors
  2023
• Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
  2024
• Inferring Functionality of Attention Heads from their Parameters
  2024