Search papers, labs, and topics across Lattice.
2
0
2
0
Reasoning validity in LLMs can be more accurately assessed through a novel three-stream detector that integrates motion with contextual state information, achieving up to 21% better accuracy than existing methods.
By tracking how LLM activations *move* through layers, this new method reveals the hidden geometry of reasoning, outperforming standard probing techniques that treat activations as static snapshots.
