arXiv Computation and Language September 14, 2026 By Minoo Ahmadi, Seyedarmin Azizi, Erfan Baghaei Potraghloo, Mehdi Kamal, Massoud Pedram

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

Read the original on arXiv Computation and Language →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

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.

By Haohui Yang, Jiaxing Sun, Xiujun Ma

llms benchmarks

arXiv AI

Jun 15

Fractured Chain-of-Thought Reasoning

arXiv:2505. 12992v4 Announce Type: replace-cross Abstract: Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining.

By Baohao Liao, Hanze Dong, Yuhui Xu, Doyen Sahoo, Christof Monz, Junnan Li, Caiming Xiong

llms benchmarks

arXiv AI

Aug 7

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

arXiv:2608. 05643v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful reasoning diversity.

By Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Lena Trigg, Ali Subhan, Muhammad Ali, Dean F. Hougen

llms reinforcement-learning

arXiv AI

Jun 2

Beyond the Frontier: Stochastic Backtracking for Efficient Test-Time Scaling

arXiv:2605. 25143v2 Announce Type: replace Abstract: Test-time scaling improves language model reasoning by spending additional compute to explore multiple solution trajectories.

By Dao Tran, Duc Anh Le, Ngoc Luu, Quan Pham, Tung Pham, Hung Bui

llms benchmarks

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

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 10

Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models

arXiv:2606. 09856v1 Announce Type: cross Abstract: Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is verifiable.

By Liyi Zhang, Akshay K. Jagadish, Brenden M. Lake, Thomas L. Griffiths

llms agents fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

More Correct Mass, Worse Answers: Why Power Sampling Can Fail and How to Fix It

Fractured Chain-of-Thought Reasoning

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

Beyond the Frontier: Stochastic Backtracking for Efficient Test-Time Scaling

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

Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models