arXiv AI
Adaptive Power Sampling for LLM Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
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 AI
Aug 5
Interpretable Adaptive Sampling for LLM Test-Time Scaling
arXiv:2608. 03961v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by generating and aggregating multiple candidate answers, yet many pipelines use fixed per-query budgets that spend the same compute on easy and difficult prompts.
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 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
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.
arXiv AI
Jul 7
A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning
arXiv:2510. 18814v4 Announce Type: replace-cross Abstract: Can language models improve their reasoning performance without external rewards, using only their own sampled responses for training?