English
Related papers

Related papers: Invariant Features in Language Models: Geometric C…

200 papers

By virtue of linguistic compositionality, few syntactic rules and a finite lexicon can generate an unbounded number of sentences. That is, language, though seemingly high-dimensional, can be explained using relatively few degrees of…

Computation and Language · Computer Science 2025-06-18 Jin Hwa Lee , Thomas Jiralerspong , Lei Yu , Yoshua Bengio , Emily Cheng

Natural language processing has made significant inroads into learning the semantics of words through distributional approaches, however representations learnt via these methods fail to capture certain kinds of information implicit in the…

Computation and Language · Computer Science 2018-07-06 Tiago Ramalho , Tomáš Kočiský , Frederic Besse , S. M. Ali Eslami , Gábor Melis , Fabio Viola , Phil Blunsom , Karl Moritz Hermann

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

Computation and Language · Computer Science 2026-01-22 Baturay Saglam , Paul Kassianik , Blaine Nelson , Sajana Weerawardhena , Yaron Singer , Amin Karbasi

Black-box probing models can reliably extract linguistic features like tense, number, and syntactic role from pretrained word representations. However, the manner in which these features are encoded in representations remains poorly…

Computation and Language · Computer Science 2021-09-15 Evan Hernandez , Jacob Andreas

A systematic way of defining variants of a modeling language is useful for adapting the language to domain or project specific needs. Variants can be obtained by adapting the syntax or semantics of the language. In this paper, we take a…

Software Engineering · Computer Science 2014-09-24 Hans Grönninger , Bernhard Rumpe

Finding semantic correspondences is a challenging problem. With the breakthrough of CNNs stronger features are available for tasks like classification but not specifically for the requirements of semantic matching. In the following we…

Computer Vision and Pattern Recognition · Computer Science 2019-06-18 Nikolai Ufer , Kam To Lui , Katja Schwarz , Paul Warkentin , Björn Ommer

Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks, these networks appear to extract generally useful linguistic…

Machine Learning · Computer Science 2019-10-29 Andy Coenen , Emily Reif , Ann Yuan , Been Kim , Adam Pearce , Fernanda Viégas , Martin Wattenberg

Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors. However, geometric properties of the continuous feature space contribute directly to the use of…

Computation and Language · Computer Science 2019-04-11 Brendan Whitaker , Denis Newman-Griffis , Aparajita Haldar , Hakan Ferhatosmanoglu , Eric Fosler-Lussier

The paper studies the local geometry of embedding clouds induced by \emph{controlled local classes of semantically close sentences}. The central question is how controlled paraphrase-like semantic variation is organized in sentence…

Computation and Language · Computer Science 2026-05-05 Leonid Bedratyuk

Understanding how neural representations respond to geometric transformations is essential for evaluating whether learned features preserve meaningful spatial structure. Existing approaches primarily assess robustness primarily by comparing…

Machine Learning · Computer Science 2026-05-12 Huahua Lin , Katayoun Farrahi , Xiaohao Cai

Existing interpretability methods for Large Language Models (LLMs) predominantly capture linear directions or isolated features. This overlooks the high-dimensional, relational, and nonlinear geometry of model representations. We apply…

Machine Learning · Computer Science 2026-04-27 Aideen Fay , Inés García-Redondo , Qiquan Wang , Haim Dubossarsky , Anthea Monod

For a language model (LM) to faithfully model human language, it must compress vast, potentially infinite information into relatively few dimensions. We propose analyzing compression in (pre-trained) LMs from two points of view: geometric…

Computation and Language · Computer Science 2023-11-10 Emily Cheng , Corentin Kervadec , Marco Baroni

Multilingual language models (LMs) promise broader NLP access, yet current systems deliver uneven performance across the world's languages. This survey examines why these gaps persist and whether they reflect intrinsic linguistic difficulty…

Computation and Language · Computer Science 2026-04-13 Chen Shani , Yuval Reif , Nathan Roll , Dan Jurafsky , Ekaterina Shutova

Contrastively pre-trained Vision-Language Models (VLMs) serve as powerful feature extractors. Yet, their shared latent spaces are prone to structural anomalies and act as repositories for non-semantic, multi-modal noise. To address this…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Jakub Grzywaczewski , Dawid Płudowski , Przemysław Biecek

Although behavioral studies have documented numerical reasoning errors in large language models (LLMs), the underlying representational mechanisms remain unclear. We hypothesize that numerical attributes occupy shared latent subspaces and…

Artificial Intelligence · Computer Science 2025-11-11 Hirohane Takagi , Gouki Minegishi , Shota Kizawa , Issey Sukeda , Hitomi Yanaka

Large pretrained language models are critical components of modern NLP pipelines. Yet, they suffer from spurious correlations, poor out-of-domain generalization, and biases. Inspired by recent progress in causal machine learning, in…

Computation and Language · Computer Science 2022-11-16 Maxime Peyrard , Sarvjeet Singh Ghotra , Martin Josifoski , Vidhan Agarwal , Barun Patra , Dean Carignan , Emre Kiciman , Robert West

GPT-style language models are sensitive to single-token changes at generation points where the predicted probability distribution is spread across multiple tokens. Viewing this sensitivity as a geometric property, we derive an…

Machine Learning · Computer Science 2026-05-12 Albert F. Modenbach

Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different…

Machine Learning · Computer Science 2025-12-02 Hanlin Yu , Berfin Inal , Georgios Arvanitidis , Soren Hauberg , Francesco Locatello , Marco Fumero

While large language models (LLMs) are trained purely on textual data, prior work has shown that their internal representations can exhibit rich geometric structure in embedding space. Building on this line of work, we investigate whether…

Artificial Intelligence · Computer Science 2026-05-28 Simardeep Singh , Paras Chopra

A central question in cognitive science is whether conceptual representations converge onto a shared manifold to support generalization, or diverge into orthogonal subspaces to minimize task interference. While prior work has discovered…

Computation and Language · Computer Science 2026-02-09 Zhimin Hu , Lanhao Niu , Sashank Varma
‹ Prev 1 2 3 10 Next ›