LLM Interpretability

ADAPT: Hybrid Prompt Optimization Advances LLM Interpretability

New research introduces ADAPT, a hybrid optimization technique that combines discrete and continuous methods to visualize and understand internal features of large language models.

LLM Interpretability

LLM Self-Explanations Can Predict Model Behavior, Study Finds

New research presents evidence that LLM self-explanations can help predict model behavior, offering a positive case for faithfulness in AI interpretability.

LLM Interpretability

Brain-Grounded Axes: Reading and Steering LLM Internal States

New research maps LLM internal representations to brain-derived axes, enabling interpretable reading and targeted steering of model behavior without fine-tuning.