English
Related papers

Related papers: Improving Value-based Process Verifier via Low-Cos…

200 papers

Large language models (LLMs) for formal theorem proving have become a prominent research focus. At present, the proving ability of these LLMs is mainly evaluated through proof pass rates on datasets such as miniF2F. However, this evaluation…

Artificial Intelligence · Computer Science 2025-02-04 Jianyu Zhang , Yongwang Zhao , Long Zhang , Jilin Hu , Xiaokun Luan , Zhiwei Xu , Feng Yang

Measurement error in count data is common but underexplored in the literature, particularly in contexts where observed scores are bounded and arise from discrete scoring processes. Motivated by applications in oral reading fluency…

Methodology · Statistics 2025-06-26 Yuqiu Yang , Christina Vu , Cornelis J. Potgieter , Xinlei Wang , Akihito Kamata

In this work, we consider the problem of estimating the probability distribution, the quantile or the conditional expectation above the quantile, the so called conditional-value-at-risk, of output quantities of complex random differential…

Computation · Statistics 2023-05-23 Quentin Ayoul-Guilmard , Sundar Ganesh , Sebastian Krumscheid , Fabio Nobile

Large language models (LLMs) often make reasoning errors when solving mathematical problems, and how to automatically detect and correct these errors has become an important research direction. However, existing approaches \textit{mainly…

Computation and Language · Computer Science 2025-11-19 Biaojie Zeng , Min Zhang , Juan Zhou , Fengrui Liu , Ruiyang Huang , Xin Lin

Large language models (LLMs) demonstrate superior reasoning capabilities compared to small language models (SLMs), but incur substantially higher costs. We propose COllaborative REAsoner (COREA), a system that cascades an SLM with an LLM to…

Computation and Language · Computer Science 2026-03-05 Chuang Zhang , Zizhen Zhu , Yihao Wei , Bing Tian , Junyi Liu , Henan Wang , Xavier Wang , Yaxiao Liu

Large Language Models (LLMs) have shown significant advances in text generation but often lack the reliability needed for autonomous deployment in high-stakes domains like healthcare, law, and finance. Existing approaches rely on external…

Artificial Intelligence · Computer Science 2024-11-12 Ninad Naik

Outcome-rewarded Large Language Models (LLMs) have demonstrated remarkable success in mathematical problem-solving. However, this success often masks a critical issue: models frequently achieve correct answers through fundamentally unsound…

Computation and Language · Computer Science 2025-06-25 Jiaxing Guo , Wenjie Yang , Shengzhong Zhang , Tongshan Xu , Lun Du , Da Zheng , Zengfeng Huang

Large language models (LLMs) have achieved remarkable performance on diverse benchmarks, yet existing evaluation practices largely rely on coarse summary metrics that obscure underlying reasoning abilities. In this work, we propose novel…

Methodology · Statistics 2026-03-17 Jia Liu , Zhiyu Xu , Yuqi Gu

While Large Language Models (LLMs) have demonstrated strong math reasoning abilities through Reinforcement Learning with *Verifiable Rewards* (RLVR), many advanced mathematical problems are proof-based, with no guaranteed way to determine…

Computation and Language · Computer Science 2026-02-20 Haotong Yang , Zitong Wang , Shijia Kang , Siqi Yang , Wenkai Yu , Xu Niu , Yike Sun , Yi Hu , Zhouchen Lin , Muhan Zhang

Small language models (SLMs) are more efficient, cost-effective, and customizable than large language models (LLMs), though they often underperform in specific areas like reasoning. Past methods for enhancing SLMs' reasoning, such as…

Computation and Language · Computer Science 2024-12-12 Kaiyuan Chen , Jin Wang , Xuejie Zhang

Process reward models (PRMs) are a cornerstone of test-time scaling (TTS), designed to verify and select the best responses from large language models (LLMs). However, this promise is challenged by recent benchmarks where simple majority…

Computation and Language · Computer Science 2026-04-24 Peng Kuang , Yanli Wang , Xiaoyu Han , Yaowenqi Liu , Kaidi Xu , Haohan Wang

Multilevel estimators aim at reducing the variance of Monte Carlo statistical estimators, by combining samples generated with simulators of different costs and accuracies. In particular, the recent work of Schaden and Ullmann (2020) on the…

Methodology · Statistics 2024-09-13 Mayeul Destouches , Paul Mycek , Selime Gürol

Evaluating Large Language Model (LLM) applications differs from traditional software testing because outputs are stochastic, high-dimensional, and sensitive to prompt and model changes. We present an evaluation-driven workflow - Define,…

Computation and Language · Computer Science 2026-01-30 Daniel Commey

Fine-tuning Large Language Models (LLMs) typically relies on large quantities of high-quality annotated data, or questions with well-defined ground truth answers in the case of Reinforcement Learning with Verifiable Rewards (RLVR). While…

Artificial Intelligence · Computer Science 2026-04-21 Justin Bauer , Thomas Walshe , Derek Pham , Harit Vishwakarma , Armin Parchami , Frederic Sala , Paroma Varma

Distributed learning methods have gained substantial momentum in recent years, with communication overhead often emerging as a critical bottleneck. Gradient compression techniques alleviate communication costs but involve an inherent…

Machine Learning · Computer Science 2025-07-09 Ze'ev Zukerman , Bassel Hamoud , Kfir Y. Levy

Bayesian inference with Markov Chain Monte Carlo (MCMC) is challenging when the likelihood function is irregular and expensive to compute. We explore several sampling algorithms that make use of subset evaluations to reduce computational…

Machine Learning · Statistics 2025-05-16 Conor Rosato , Harvinder Lehal , Simon Maskell , Lee Devlin , Malcolm Strens

Process reward models (PRMs) play a central role in guiding inference-time scaling algorithms for large language models (LLMs). However, we observe that even state-of-the-art PRMs can be poorly calibrated. Specifically, they tend to…

Machine Learning · Statistics 2025-11-10 Young-Jin Park , Kristjan Greenewald , Kaveh Alim , Hao Wang , Navid Azizan

Sequential Monte Carlo (SMC) samplers for reward-guided diffusion models often suffer from rapid lineage collapse: a few high-reward particles dominate the population within a handful of resampling steps, destroying diversity and degrading…

Artificial Intelligence · Computer Science 2026-05-13 Shivanshu Shekhar , Sagnik Mukherjee , Jia Yi Zhang , Tong Zhang

Developing prompt-based methods with Large Language Models (LLMs) requires making numerous decisions, which give rise to a combinatorial search problem over hyper-parameters. This exhaustive evaluation can be time-consuming and costly. In…

Artificial Intelligence · Computer Science 2025-02-28 Jin Peng Zhou , Christian K. Belardi , Ruihan Wu , Travis Zhang , Carla P. Gomes , Wen Sun , Kilian Q. Weinberger

We present GSM-MC, a multiple-choice (MC) dataset constructed by collecting answers and incorrect predictions on GSM8K from 60 open-source models. Through extensive experiments, we show that LLMs' performance on the MC version of this…

Computation and Language · Computer Science 2024-06-27 Ziyin Zhang , Zhaokun Jiang , Lizhen Xu , Hongkun Hao , Rui Wang
‹ Prev 1 3 4 5 6 7 10 Next ›