SOURCE-LINKED INTELLIGENCE

Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

A prominent paradigm in inference-time alignment employs lightweight supervisors to steer Large Language Models (LLMs). Through empirical analysis, we identify a structural mismatch in this paradigm: weak supervisors exhibit pervasive high entropy across the vast majority of tokens, yet prevailing dense intervention approaches mandate supervision at every decoding step. This leads to frequent low-confidence interventions that can disrupt valid base-model reasoning and incur substantial utility costs. To resolve this, we propose TUSA (Trust-based Uncertainty Sparse Alignment). Moving away from

Read original source ↗ Open in workspace

recordType

paper

region

Global