arXiv AI

Reasoning with Sampling: Cutting at Decision Points

arXiv Machine Learning
Sep 14

Sampling via Decision-Flow: Training-Free Extraction of Improved Latent Reasoning Paths in Large Language Models

The paper introduces Decision-Flow Sampling (DF‑Sample), a training‑free, data‑free inference framework that builds a hierarchical reasoning tree, evaluates entire trajectories, and back‑propagates utilities to guide branching decisions. Unlike local step‑wise sampling, DF‑Sample explicitly assesses global paths, enabling it to recover high‑quality, low‑probability reasoning chains that standard decoding misses. On the GPQA benchmark, DF‑Sample attains 45.6% accuracy, outperforming power sampling (38.9%) and GRPO (39.9%) and consistently surpassing baselines across multiple models and benchmarks, demonstrating significant latent reasoning potential in pretrained LLMs.

By Zhendong Mi, Shaoyi Huang
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.

By Minoo Ahmadi, Seyedarmin Azizi, Erfan Baghaei Potraghloo, Mehdi Kamal, Massoud Pedram
arXiv AI
Jun 10

Sample Where You Struggle: Sharpening Base Model Reasoning via Entropy-Guided Power Sampling

arXiv:2606. 09926v1 Announce Type: cross Abstract: Sampling from the sequence-level power distribution $p^\alpha$ elicits RL-level reasoning from base language models without any parameter updates, but the standard Metropolis--Hastings (MH), a Markov Chain Monte Carlo (MCMC) sampler, is both expensive and slow-mixing.

By Hong Guo, Nianhui Guo, Christoph Meinel, Haojin Yang
arXiv AI
Oct 15

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.

By Xiaotong Ji, Rasul Tutunov, Matthieu Zimmer, Haitham Bou Ammar
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×.

By Seyedarmin Azizi, Erfan Baghaei Potraghloo, Minoo Ahmadi, Souvik Kundu, Massoud Pedram
arXiv AI
Sep 11

Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reasoning

The paper introduces Trimmed Logit-Gap SFT (TrimSFT), a token-level reweighting strategy that adjusts supervised fine-tuning loss based on the logit gap between the correct token and its strongest competitor. TrimSFT trims supervision from tokens that are either already mastered (large logit gap) or poorly supported (small or negative logit gap), focusing learning on tokens with intermediate logit gaps. Experiments on six base models across five mathematical reasoning benchmarks show that TrimSFT consistently outperforms standard SFT, achieving the best average performance on five of six models and up to +26.9 points on MATH500.

By Yaning Jia, Chunhui Zhang, Wenxuan Xu, Xingjian Diao, Xiaoyuan Wang, Soroush Vosoughi
Hugging Face Trending Papers
Jun 1

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning

Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small model has already committed to incorrect reasoning paths. PRM guided search avoids this by scoring candidate continuations during generation, but requires a reward model trained with step-level labels.