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

Jul 14, 2026

SPARK uses hidden-state response to diagnose whether a large language model (LLM) internally enters an effective reasoning state and to guide lightweight test-time steering. The method improves Qwen3 models on the MATH-500 benchmark, increasing accuracy from 82.0% to 84.6% for Qwen3-4B and from 82.4% to 85.6% for Qwen3-8B.

Why it matters: This approach provides a diagnostic signal for reasoning failures and a practical guide for targeted test-time intervention in LLMs.

Full story at: arXiv AI/ML ↗