Jade (Lei) Yu
Open Menu
Close Menu
Bio
Papers
News
Experience
Article-Journal
The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction
Jan 1, 2025
Infinite Mixture Chaining: An Efficiency-Based Framework for the Dynamic Construction of Word Meaning
Jan 1, 2025
Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations
Jan 1, 2025
Robust LLM safeguarding via refusal feature adversarial training
Jan 1, 2024
Mechanistic understanding and mitigation of language model non-factual hallucinations
Jan 1, 2024
Mechanisms of non-factual hallucinations in language models
Jan 1, 2024
Intrinsic evaluation of unlearning using parametric knowledge traces
Jan 1, 2024
Geometric Signatures of Compositionality Across a Language Model's Lifetime
Jan 1, 2024
Functional faithfulness in the wild: Circuit discovery with differentiable computation graph pruning
Jan 1, 2024
Emergence of a high-dimensional abstraction phase in language transformers
Jan 1, 2024
Next »