English
Related papers

Related papers: LLMs are Bayesian, In Expectation, Not in Realizat…

200 papers

In-context learning (ICL) enables transformers to adapt to new tasks through contextual examples without parameter updates. While existing research has typically studied ICL in fixed-complexity environments, practical language models…

Machine Learning · Computer Science 2025-06-25 Puneesh Deora , Bhavya Vasudeva , Tina Behnia , Christos Thrampoulidis

Recent advances in reasoning techniques have substantially improved the performance of large language models (LLMs), raising expectations for their ability to provide accurate, truthful, and reliable information. However, emerging evidence…

Artificial Intelligence · Computer Science 2025-12-03 Zhonghao He , Tianyi Qiu , Hirokazu Shirado , Maarten Sap

In-context learning, a capability that enables a model to learn from input examples on the fly without necessitating weight updates, is a defining characteristic of large language models. In this work, we follow the setting proposed in…

Machine Learning · Computer Science 2023-05-29 Kartik Ahuja , David Lopez-Paz

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

Bayesian supervised predictive classifiers, hypothesis testing, and parametric estimation under Partition Exchangeability are implemented. The two classifiers presented are the marginal classifier (that assumes test data is i.i.d.) next to…

Computation · Statistics 2021-12-06 Ville Kinnula , Jing Tang , Ali Amiryousefi

With the attention mechanism, transformers achieve significant empirical successes. Despite the intuitive understanding that transformers perform relational inference over long sequences to produce desirable representations, we lack a…

Machine Learning · Computer Science 2024-04-02 Yufeng Zhang , Boyi Liu , Qi Cai , Lingxiao Wang , Zhaoran Wang

We showcase how dropout variational inference can be applied to a large-scale deep learning model that predicts price movements from limit order books (LOBs), the canonical data source representing trading and pricing movements. We…

Computational Finance · Quantitative Finance 2019-03-26 Zihao Zhang , Stefan Zohren , Stephen Roberts

Large language models demonstrate strong performance on mathematical reasoning benchmarks, yet remain surprisingly fragile to meaning-preserving surface perturbations. We systematically evaluate three open-weight LLMs, Mistral-7B,…

Computation and Language · Computer Science 2026-04-03 Shou-Tzu Han , Rodrigue Rizk , KC Santosh

Modern challenges of robustness, fairness, and decision-making in machine learning have led to the formulation of multi-distribution learning (MDL) frameworks in which a predictor is optimized across multiple distributions. We study the…

Machine Learning · Computer Science 2024-12-19 Rajeev Verma , Volker Fischer , Eric Nalisnick

We study Transformer overparameterization through the lens of angular similarity in high-dimensional encoder-decoder embeddings. We apply Bernoulli dropout between the encoder and the decoder, varying the keep probability $p$ to identify a…

Machine Learning · Computer Science 2026-01-27 Xuanzhou Chen

Prior behavioural work suggests that some LLMs alter choices when options are framed as causing pain or pleasure, and that such deviations can scale with stated intensity. To bridge behavioural evidence (what the model does) with…

Artificial Intelligence · Computer Science 2026-02-24 Francesca Bianco , Derek Shiller

In the analysis of machine learning models, it is often convenient to assume that the parameters are IID. This assumption is not satisfied when the parameters are updated through training processes such as SGD. A relaxation of the IID…

Machine Learning · Computer Science 2018-10-30 Russell Tsuchida , Fred Roosta , Marcus Gallagher

This paper investigates the counterintuitive phenomenon where fine-tuning pre-trained transformer models degrades performance on the MS MARCO passage ranking task. Through comprehensive experiments involving five model variants-including…

Computation and Language · Computer Science 2025-06-24 Manu Pande , Shahil Kumar , Anay Yatin Damle

Spatio-temporal hidden Markov models are extremely difficult to estimate because their latent joint distributions are available only in trivial cases. In the estimation phase, these latent distributions are usually substituted with…

Methodology · Statistics 2025-09-19 Daniele Tancini , Riccardo Rastelli , Francesco Bartolucci

We present a novel model architecture which leverages deep learning tools to perform exact Bayesian inference on sets of high dimensional, complex observations. Our model is provably exchangeable, meaning that the joint distribution over…

Machine Learning · Statistics 2018-10-17 Iryna Korshunova , Jonas Degrave , Ferenc Huszár , Yarin Gal , Arthur Gretton , Joni Dambre

Transfer learning (TL) has emerged as a powerful tool to supplement data collected for a target task with data collected for a related source task. The Bayesian framework is natural for TL because information from the source data can be…

Methodology · Statistics 2024-06-06 Mohamed A. Abba , Jonathan P. Williams , Brian J. Reich

We consider the problem of identifying parameters of a particular class of Markov chains, called Bernoulli Autoregressive (BAR) processes. The structure of any BAR model is encoded by a directed graph. Incoming edges to a node in the graph…

Statistics Theory · Mathematics 2020-10-20 Xiaotian Xie , Dimitrios Katselis , Carolyn L. Beck , R. Srikant

We propose Evolutionary Dynamic Loss (EDL), a framework that learns a transferable classification loss in the probability space using unlimited synthetic prediction-label pairs, without accessing real samples during the main loss…

Machine Learning · Computer Science 2026-05-06 Meng Xiang , Yan Pei

We propose a new Bayesian Neural Net formulation that affords variational inference for which the evidence lower bound is analytically tractable subject to a tight approximation. We achieve this tractability by (i) decomposing ReLU…

Machine Learning · Statistics 2019-06-13 Manuel Haussmann , Fred A. Hamprecht , Melih Kandemir

LLMs demonstrate remarkable reasoning capabilities, yet whether they utilize internal world models or rely on sophisticated pattern matching remains open. We study LLMs through the lens of robustness of their code understanding using a…

Software Engineering · Computer Science 2026-04-21 Claudio Spiess , Prem Devanbu , Earl T. Barr