English
Related papers

Related papers: Probabilistic Inference in Language Models via Twi…

200 papers

Accurately quantifying uncertainty in large language models (LLMs) is crucial for their reliable deployment, especially in high-stakes applications. Current state-of-the-art methods for measuring semantic uncertainty in LLMs rely on strict…

Machine Learning · Computer Science 2024-10-31 Yashvir S. Grewal , Edwin V. Bonilla , Thang D. Bui

Large Language Models (LLMs), such as GPT, are considered to learn the latent distributions within large-scale web-crawl datasets and accomplish natural language processing (NLP) tasks by predicting the next token. However, this mechanism…

Computation and Language · Computer Science 2025-02-04 Kun-Peng Ning , Jia-Yu Yao , Yu-Yang Liu , Mu-Nan Ning , Li Yuan

This article reviews the application of advanced Monte Carlo techniques in the context of Multilevel Monte Carlo (MLMC). MLMC is a strategy employed to compute expectations which can be biased in some sense, for instance, by using the…

Computation · Statistics 2017-04-25 Ajay Jasra , Kody Law , Carina Suciu

We propose a new framework for how to use sequential Monte Carlo (SMC) algorithms for inference in probabilistic graphical models (PGM). Via a sequential decomposition of the PGM we find a sequence of auxiliary distributions defined on a…

Methodology · Statistics 2014-10-07 Christian A. Naesseth , Fredrik Lindsten , Thomas B. Schön

Inference-time scaling has achieved remarkable success in language models, yet its adaptation to diffusion models remains underexplored. We observe that the efficacy of recent Sequential Monte Carlo (SMC)-based methods largely stems from…

Machine Learning · Computer Science 2025-08-19 Xun Su , Jianming Huang , Yang Yusen , Zhongxi Fang , Hiroyuki Kasai

In this article we develop a new sequential Monte Carlo (SMC) method for multilevel (ML) Monte Carlo estimation. In particular, the method can be used to estimate expectations with respect to a target probability distribution over an…

Computation · Statistics 2017-03-16 Alexandros Beskos , Ajay Jasra , Kody Law , Youssef Marzouk , Yan Zhou

In this article we consider the approximation of expectations w.r.t. probability distributions associated to the solution of partial differential equations (PDEs); this scenario appears routinely in Bayesian inverse problems. In practice,…

Computation · Statistics 2017-02-07 Alexandros Beskos , Ajay Jasra , Kody Law , Raul Tempone , Yan Zhou

Pre-trained Large Language Models (LLMs) encapsulate large amounts of knowledge and take enormous amounts of compute to train. We make use of this resource, together with the observation that LLMs are able to transfer knowledge and…

Machine Learning · Computer Science 2025-01-14 Malcolm L. Wolff , Shenghao Yang , Kari Torkkola , Michael W. Mahoney

Machine learning and deep learning have revolutionized computational physics, particularly the simulation of complex systems. Equivariance is essential for simulating physical systems because it imposes a strong inductive bias on the…

Strongly Correlated Electrons · Physics 2024-11-13 Yuki Nagai , Akio Tomiya

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks. However, the truthfulness of their outputs is not guaranteed, and their tendency toward overconfidence further limits reliability. Uncertainty…

Computation and Language · Computer Science 2026-03-23 Qi Cao , Andrew Gambardella , Takeshi Kojima , Yutaka Matsuo , Yusuke Iwasawa

Large language models generate outputs stochastically and may produce fluent but invalid responses, including factual hallucinations. Existing mitigation strategies reduce average error rates but do not provide explicit control over the…

Machine Learning · Computer Science 2026-02-03 Sreenivasan Mohandas

We establish epigraphical and uniform laws of large numbers for sample-based approximations of law invariant risk functionals. These sample-based approximation schemes include Monte Carlo (MC) and certain randomized quasi-Monte Carlo…

Optimization and Control · Mathematics 2025-07-01 Olena Melnikov , Johannes Milz

We propose a novel sequential Monte Carlo (SMC) method for sampling from unnormalized target distributions based on a reverse denoising diffusion process. While recent diffusion-based samplers simulate the reverse diffusion using…

Computation · Statistics 2025-11-06 Luhuan Wu , Yi Han , Christian A. Naesseth , John P. Cunningham

Trans-dimensional random field language models (TRF LMs) have recently been introduced, where sentences are modeled as a collection of random fields. The TRF approach has been shown to have the advantages of being computationally more…

Computation and Language · Computer Science 2017-09-20 Bin Wang , Zhijian Ou

We consider the problem of estimating expectations with respect to a target distribution with an unknown normalizing constant, and where even the unnormalized target needs to be approximated at finite resolution. Under such an assumption,…

Numerical Analysis · Mathematics 2023-06-29 Xinzhu Liang , Shangda Yang , Simon L. Cotter , Kody J. H. Law

Constrained decoding enables Language Models (LMs) to produce samples that provably satisfy hard constraints. However, existing constrained-decoding approaches often distort the underlying model distribution, a limitation that is especially…

Artificial Intelligence · Computer Science 2025-06-09 Emmanuel Anaya Gonzalez , Sairam Vaidya , Kanghee Park , Ruyi Ji , Taylor Berg-Kirkpatrick , Loris D'Antoni

Trans-dimensional random field language models (TRF LMs) where sentences are modeled as a collection of random fields, have shown close performance with LSTM LMs in speech recognition and are computationally more efficient in inference.…

Computation and Language · Computer Science 2017-10-31 Bin Wang , Zhijian Ou

Monte-Carlo tree search (MCTS) has driven many recent breakthroughs in deep reinforcement learning (RL). However, scaling MCTS to parallel compute has proven challenging in practice which has motivated alternative planners like sequential…

Machine Learning · Computer Science 2025-07-09 Joery A. de Vries , Jinke He , Yaniv Oren , Matthijs T. J. Spaan

Langevin Monte Carlo (LMC) algorithms are popular Markov Chain Monte Carlo (MCMC) methods to sample a target probability distribution, which arises in many applications in machine learning. Inspired by regime-switching stochastic…

Computation · Statistics 2025-09-03 Xiaoyu Wang , Yingli Wang , Lingjiong Zhu

Urban congestion remains a critical challenge, with traffic signal control (TSC) emerging as a potent solution. TSC is often modeled as a Markov Decision Process problem and then solved using reinforcement learning (RL), which has proven…

Artificial Intelligence · Computer Science 2024-07-09 Aoyu Pang , Maonan Wang , Man-On Pun , Chung Shue Chen , Xi Xiong