04:00
2026-09-14
arxiv.org
large-language-models
Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding
Researchers introduced Chopthin-Consensus Power Sampling (CCPS), a training-free LLM decoding method that applies the Chopthin resampler to Sequential Monte Carlo inference to preserve reasoning-path …