SOURCE-LINKED INTELLIGENCE

Beyond Truncation: Rethinking LLM Decoding as Ensemble Pruning

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

We introduce Mahalanobis-Ensemble Decoding (ME-Decoding), a novel Large Language Model (LLM) decoding framework that frames candidate token selection as ensemble pruning. Existing selection strategies rely predominantly on scalar probabilities, ignoring geometric semantic relationships and causing candidate redundancy. Meanwhile, current geometry-aware methods often require complex optimization or directly reweighting the original token probabilities, leading to significant computational overhead or inference instability. To address this, we formulate decoding as a subset optimization problem

Read original source ↗ Open in workspace

recordType

paper

region

Global