arXiv Machine Learning
Decoupled Marginal Sharpening for Training-Free Inference-Time Scaling
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Oct 5
Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning
Power‑SMC is a training‑free sampling method that targets the sequence‑level power distribution used to sharpen large language model outputs for reasoning tasks. It maintains multiple candidate sequences, assigns importance weights based on how well each matches the power distribution, and periodically prunes low‑scoring candidates to keep inference latency close to standard decoding. Experiments on MATH500, GSM8K, GPQA, and HumanEval show that Power‑SMC matches or surpasses Metropolis–Hastings sampling in accuracy, preserves output diversity, and can accelerate inference speed by up to 17.6×.
arXiv Machine Learning
Sep 30
Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling
arXiv:2609.38104v1 Announce Type: new Abstract: Power-sharpened sampling is an inference-time alternative to reinforcement-learning (RL) post-training for enhancing reasoning in large language models...
arXiv Computation and Language
Sep 14
Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding
Chopthin-Consensus Power Sampling (CCPS) is a new inference-time decoding method for large language models that uses the Chopthin resampler to preserve diversity among particle trajectories. By enforcing an upper bound on weight ratios instead of equal-weight resampling, CCPS maintains a richer set of distinct reasoning paths and guarantees a lower bound on effective sample size. Coupled with a semantic-majority selection mechanism, CCPS achieves higher oracle coverage and matches or surpasses baseline accuracy on multiple reasoning benchmarks.
arXiv AI
Sep 30
Reasoning with Sampling: Cutting at Decision Points
arXiv:2605.30327v2 Announce Type: replace-cross Abstract: Frontier reasoning models are produced by post-training base language models with reinforcement learning. Recent work has challenged this by...
arXiv AI
4d ago
Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
The paper introduces Scalable Power Sampling, a training‑free method that sharpens a large language model’s generative distribution by approximating the autoregressive power distribution with a token‑level scaled low‑temperature distribution. This approach eliminates the need for iterative Markov chain Monte Carlo, achieving performance comparable to or better than one‑shot GRPO on math, QA, and code tasks while cutting inference latency by more than tenfold. The method relies solely on the base model’s outputs, requiring no external rewards or verifiers.
arXiv Machine Learning
Aug 17
More Correct Mass, Worse Answers: Why Power Sampling Can Fail and How to Fix It
arXiv:2608. 14420v1 Announce Type: new Abstract: Power Sampling sharpens a language model's distribution over complete generation trajectories, offering a verifier-free way to improve reasoning at inference time.