SOURCE-LINKED INTELLIGENCE

Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Inference-time power sampling via Sequential Monte Carlo (SMC) can substantially improve large language model (LLM) reasoning without requiring post-training. However, many existing SMC approaches rely on equal-weight resampling, which can aggressively prune low-weight trajectories, discarding potentially correct reasoning paths and degrading the genealogical diversity of the search space. To address this, we introduce Chopthin-Consensus Power Sampling (CCPS). Our method applies the Chopthin resampler to LLM decoding: rather than equalizing weights and forcing unnecessary particle duplication,

Read original source ↗ Open in workspace

recordType

paper

region

Global