English
Related papers

Related papers: Toward a Flexible Framework for Linear Representat…

200 papers

Analogical reasoning relies on conceptual abstractions, but it is unclear whether Large Language Models (LLMs) harbor such internal representations. We explore distilled representations from LLM activations and find that function vectors…

Computation and Language · Computer Science 2025-03-06 Gustaw Opiełka , Hannes Rosenbusch , Claire E. Stevenson

We develop a pseudo-likelihood theory for rank one matrix estimation problems in the high dimensional limit. We prove a variational principle for the limiting pseudo-maximum likelihood which also characterizes the performance of the…

Statistics Theory · Mathematics 2025-11-10 Curtis Grant , Aukosh Jagannath , Justin Ko

Interpreting individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making processes and ensuring AI safety. Despite recent progress in neuron labeling, existing methods often limit the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Vladimir Zaigrajew , Michał Piechota , Gaspar Sekula , Paweł Gelar , Przemysław Biecek

Generalized linear models (GLMs) are fundamental tools for statistical modeling, with maximum likelihood estimation (MLE) serving as the classical approach for parameter inference. While MLE performs well for canonical GLMs, it can become…

Methodology · Statistics 2026-03-03 Linglingzhi Zhu , Jonghyeok Lee , Yao Xie

Concept Bottleneck Models (CBMs) provide a basis for semantic abstractions within a neural network architecture. Such models have primarily been seen through the lens of interpretability so far, wherein they offer transparency by inferring…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Deepika SN Vemuri , Gautham Bellamkonda , Aditya Pola , Vineeth N Balasubramanian

Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research. Existing feature interpretability methods often rely on strong assumptions about the structure of…

Machine Learning · Computer Science 2025-09-30 Yifan Luo , Zhennan Zhou , Bin Dong

Embeddings have become a pivotal means to represent complex, multi-faceted information about entities, concepts, and relationships in a condensed and useful format. Nevertheless, they often preclude direct interpretation. While downstream…

Representation learning is a fundamental building block for analyzing entities in a database. While the existing embedding learning methods are effective in various data mining problems, their applicability is often limited because these…

Machine Learning · Computer Science 2020-09-24 Chin-Chia Michael Yeh , Dhruv Gelda , Zhongfang Zhuang , Yan Zheng , Liang Gou , Wei Zhang

An important line of research attempts to explain CNN image classifier predictions and intermediate layer representations in terms of human-understandable concepts. Previous work supports that deep representations are linearly separable…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Alexandros Doumanoglou , Stylianos Asteriadis , Dimitrios Zarpalas

Uncertainty in machine learning refers to the degree of confidence or lack thereof in a model's predictions. While uncertainty quantification methods exist, explanations of uncertainty, especially in high-dimensional settings, remain an…

Machine Learning · Computer Science 2025-07-30 Isaac Roberts , Alexander Schulz , Sarah Schroeder , Fabian Hinder , Barbara Hammer

A challenge in advancing Visual-Language Models (VLMs) is determining whether their failures on abstract reasoning tasks, such as Bongard problems, stem from flawed perception or faulty top-down reasoning. To disentangle these factors, we…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Enrico Vompa , Tanel Tammet , Mohit Vaishnav

We propose a new way of thinking about deep neural networks, in which the linear and non-linear components of the network are naturally derived and justified in terms of principles in probability theory. In particular, the models…

Machine Learning · Computer Science 2019-10-11 Amir Emad Marvasti , Ehsan Emad Marvasti , George Atia , Hassan Foroosh

The trade-off between accuracy and interpretability has long been a challenge in machine learning (ML). This tension is particularly significant for emerging interpretable-by-design methods, which aim to redesign ML algorithms for…

Machine Learning · Computer Science 2025-05-28 Geyu Liang , Senne Michielssen , Salar Fattahi

Neural language models (LMs) perform well on tasks that require sensitivity to syntactic structure. Drawing on the syntactic priming paradigm from psycholinguistics, we propose a novel technique to analyze the representations that enable…

Computation and Language · Computer Science 2019-09-25 Grusha Prasad , Marten van Schijndel , Tal Linzen

Activation steering methods in large language models (LLMs) have emerged as an effective way to perform targeted updates to enhance generated language without requiring large amounts of adaptation data. We ask whether the features…

Computation and Language · Computer Science 2025-11-05 Masha Fedzechkina , Eleonora Gualdoni , Sinead Williamson , Katherine Metcalf , Skyler Seto , Barry-John Theobald

The output of Large Language Models (LLMs) are a function of the internal model's parameters and the input provided into the context window. The hypothesis presented here is that under a greedy sampling strategy the variance in the LLM's…

Artificial Intelligence · Computer Science 2025-02-20 Srijith Rajamohan , Ahmed Salhin , Josh Frazier , Rohit Kumar , Yu-Cheng Tsai , Todd Cook

In this paper, we establish a unified framework for subspace identification (SID) of linear parameter-varying (LPV) systems to estimate LPV state-space (SS) models in innovation form. This framework enables us to derive novel LPV SID…

Systems and Control · Electrical Eng. & Systems 2020-08-11 P. B. Cox , R. Tóth

Across scientific domains, a fundamental challenge is to characterize and compute the mappings from underlying physical processes to observed signals and measurements. While nonlinear neural networks have achieved considerable success, they…

Machine Learning · Computer Science 2025-08-11 Alexander DeLise , Kyle Loh , Krish Patel , Meredith Teague , Andrea Arnold , Matthias Chung

Large Language Models (LLMs) frequently generate plausible but non-factual content, a phenomenon known as hallucination. While existing detection methods typically rely on computationally expensive sampling-based consistency checks or…

Machine Learning · Computer Science 2026-05-07 Dan Wilson , Mohamed Akrout

Large language models (LLMs) are known to perpetuate stereotypes and exhibit biases. Various strategies have been proposed to mitigate these biases, but most work studies biases as a black-box problem without considering how concepts are…

Computation and Language · Computer Science 2025-09-19 Hannah Cyberey , Yangfeng Ji , David Evans