SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models

The SPARK framework profiles and steers the latent reasoning states of large language models to diagnose and correct reasoning failures before final outputs are generated.

Firefly links to the original publisher. The summary above is AI-generated for orientation and may differ from the source. The “current rank score” decays over time so newer significant stories surface first.