English
Related papers

Related papers: Variational Uncertainty Decomposition for In-Conte…

200 papers

Previous work has showcased the intriguing capability of large language models (LLMs) in retrieving facts and processing context knowledge. However, only limited research exists on the layer-wise capability of LLMs to encode knowledge,…

Computation and Language · Computer Science 2024-03-05 Tianjie Ju , Weiwei Sun , Wei Du , Xinwei Yuan , Zhaochun Ren , Gongshen Liu

Topic models are Bayesian models that are frequently used to capture the latent structure of certain corpora of documents or images. Each data element in such a corpus (for instance each item in a collection of scientific articles) is…

Machine Learning · Statistics 2018-02-05 Behrooz Ghorbani , Hamid Javadi , Andrea Montanari

Intelligent agents must be able to articulate its own uncertainty. In this work, we show that pre-trained sequence models are naturally capable of probabilistic reasoning over exchangeable data points -- forming informed beliefs and…

Machine Learning · Statistics 2024-12-02 Naimeng Ye , Hongseok Namkoong

Previous theoretical results pertaining to meta-learning on sequences build on contrived assumptions and are somewhat convoluted. We introduce new information-theoretic tools that lead to an elegant and very general decomposition of error…

Machine Learning · Computer Science 2024-01-30 Hong Jun Jeon , Jason D. Lee , Qi Lei , Benjamin Van Roy

This work studies the class of algorithms for learning with side-information that emerge by extending generative models with embedded context-related variables. Using finite mixture models (FMM) as the prototypical Bayesian network, we show…

Machine Learning · Statistics 2020-08-17 Serafeim Perdikis , Robert Leeb , Ricardo Chavarriaga , José del R. Millán

Question decomposition has emerged as an effective strategy for prompting Large Language Models (LLMs) to answer complex questions. However, while existing methods primarily focus on unimodal language models, the question decomposition…

Computation and Language · Computer Science 2024-10-08 Haowei Zhang , Jianzhe Liu , Zhen Han , Shuo Chen , Bailan He , Volker Tresp , Zhiqiang Xu , Jindong Gu

There has been much recent, exciting work on combining the complementary strengths of latent variable models and deep learning. Latent variable modeling makes it easy to explicitly specify model constraints through conditional independence…

Computation and Language · Computer Science 2019-08-06 Yoon Kim , Sam Wiseman , Alexander M. Rush

Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via greedy decoding. However, we find that deterministic evaluations fail to capture…

Machine Learning · Computer Science 2025-03-04 Yan Scholten , Stephan Günnemann , Leo Schwinn

In this work, we evaluate the potential of Large Language Models (LLMs) in building Bayesian Networks (BNs) by approximating domain expert priors. LLMs have demonstrated potential as factual knowledge bases; however, their capability to…

Computation and Language · Computer Science 2025-08-12 Aliakbar Nafar , Kristen Brent Venable , Zijun Cui , Parisa Kordjamshidi

Supervised machine learning and predictive models have achieved an impressive standard today, enabling us to answer questions that were inconceivable a few years ago. Besides these successes, it becomes clear, that beyond pure prediction,…

Machine Learning · Statistics 2025-01-29 Cornelia Gruber , Patrick Oliver Schenk , Malte Schierholz , Frauke Kreuter , Göran Kauermann

Large language models (LLMs) have revolutionized the field of natural language processing with their impressive reasoning and question-answering capabilities. However, these models are sometimes prone to generating credible-sounding but…

Computation and Language · Computer Science 2026-04-21 Ranganath Krishnan , Piyush Khanna , Omesh Tickoo

This thesis investigates two key phenomena in large language models (LLMs): in-context learning (ICL) and model collapse. We study ICL in a linear transformer with tied weights trained on linear regression tasks, and show that minimising…

Artificial Intelligence · Computer Science 2026-01-06 Josef Ott

Large language models (LLMs) have demonstrated their ability to learn in-context, allowing them to perform various tasks based on a few input-output examples. However, the effectiveness of in-context learning is heavily reliant on the…

Computation and Language · Computer Science 2024-01-29 Liang Wang , Nan Yang , Furu Wei

Predicting simple function classes has been widely used as a testbed for developing theory and understanding of the trained Transformer's in-context learning (ICL) ability. In this paper, we revisit the training of Transformers on linear…

Machine Learning · Computer Science 2024-05-27 Shang Liu , Zhongze Cai , Guanting Chen , Xiaocheng Li

In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Haoyu Wang , Haonan Wang , Yuyan Chen , Jun Chen , Gang Liu , Qian Wang , Jiahong Yan , Yanghua Xiao

Deep learning has achieved impressive performance on many tasks in recent years. However, it has been found that it is still not enough for deep neural networks to provide only point estimates. For high-risk tasks, we need to assess the…

Machine Learning · Computer Science 2021-04-28 Yuandu Lai , Yucheng Shi , Yahong Han , Yunfeng Shao , Meiyu Qi , Bingshuai Li

Large Language Models (LLMs) are powerful linguistic engines but remain susceptible to hallucinations: plausible-sounding outputs that are factually incorrect or unsupported. In this work, we present a mathematically grounded framework to…

Computation and Language · Computer Science 2025-11-20 Moses Kiprono

Deep neural networks have achieved impressive results on a wide variety of tasks. However, quantifying uncertainty in the network's output is a challenging task. Bayesian models offer a mathematical framework to reason about model…

Machine Learning · Computer Science 2019-05-28 Manikanta Srikar Yellapragada , Chandra Prakash Konkimalla

In this paper we motivate the causal mechanisms behind sample selection induced collider bias (selection collider bias) that can cause Large Language Models (LLMs) to learn unconditional dependence between entities that are unconditionally…

Computation and Language · Computer Science 2022-09-14 Emily McMilin

As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial. While modern neural networks are making remarkable gains in terms of predictive accuracy, characterizing…

Machine Learning · Computer Science 2019-06-14 Melanie F. Pradier , Weiwei Pan , Jiayu Yao , Soumya Ghosh , Finale Doshi-velez