Cover Image

Language Models Learn Universal Representations of Numbers and Here's Why You Should Care

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Štefánik, Michal, Mickus, Timothee, Kadlčík, Marek, Højer, Bertram, Spiegel, Michal, Vázquez, Raúl, Sinha, Aman, Kuchař, Josef, Mondorf, Philipp, Stenetorp, Pontus
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning Neural and Evolutionary Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Pre-trained Language Models Learn Remarkably Accurate Representations of Numbers
by: Kadlčík, Marek, et al.
Published: (2025)

Can Out-of-Distribution Evaluations Uncover Reliance on Shortcuts? A Case Study in Question Answering
by: Štefánik, Michal, et al.
Published: (2025)

VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics
by: Kuchař, Josef, et al.
Published: (2025)

Attend or Perish: Benchmarking Attention in Algorithmic Reasoning
by: Spiegel, Michal, et al.
Published: (2025)

Self-training Language Models for Arithmetic Reasoning
by: Kadlčík, Marek, et al.
Published: (2024)

Negation: A Pink Elephant in the Large Language Models' Room?
by: Vrabcová, Tereza, et al.
Published: (2025)

Concept-aware Data Construction Improves In-context Learning of Language Models
by: Štefánik, Michal, et al.
Published: (2024)

Your Model is Overconfident, and Other Lies We Tell Ourselves
by: Mickus, Timothee, et al.
Published: (2025)

Improving Language Plasticity via Pretraining with Active Forgetting
by: Chen, Yihong, et al.
Published: (2023)

Balancing Pareto Front exploration of Non-dominated Tournament Genetic Algorithm (B-NTGA) in solving multi-objective NP-hard problems with constraints
by: Antkiewicz, Michał, et al.
Published: (2024)

Evolutionary feature selection for spiking neural network pattern classifiers
by: Valko, Michal, et al.
Published: (2026)

The hop-like problem nature -- unveiling and modelling new features of real-world problems
by: Przewozniczek, Michal W., et al.
Published: (2024)

Brain-inspired Computational Modeling of Action Recognition with Recurrent Spiking Neural Networks Equipped with Reinforcement Delay Learning
by: Nadafian, Alireza, et al.
Published: (2024)

I Have an Attention Bridge to Sell You: Generalization Capabilities of Modular Translation Architectures
by: Mickus, Timothee, et al.
Published: (2024)

Why Evolve When You Can Adapt? Post-Evolution Adaptation of Genetic Memory for On-the-Fly Control
by: Hammami, Hamze, et al.
Published: (2025)

DelRec: learning delays in recurrent spiking neural networks
by: Queant, Alexandre, et al.
Published: (2025)

Availability of Perfect Decomposition in Statistical Linkage Learning for Unitation-based Function Concatenations
by: Prusik, Michal, et al.
Published: (2025)

Parametric-Task MAP-Elites
by: Anne, Timothée, et al.
Published: (2024)

Metaheuristics is All You Need
by: Cuicizion, Eliuvish, et al.
Published: (2024)

Neuro-Vesicles: Neuromodulation Should Be a Dynamical System, Not a Tensor Decoration
by: Li, Zilin, et al.
Published: (2025)

Adversarial Coevolutionary Illumination with Generational Adversarial MAP-Elites
by: Anne, Timothée, et al.
Published: (2025)

Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics
by: Xue, Peng, et al.
Published: (2025)

Tournament Informed Adversarial Quality Diversity
by: Anne, Timothée, et al.
Published: (2026)

Efficiently Training Time-to-First-Spike Spiking Neural Networks from Scratch
by: Che, Kaiwei, et al.
Published: (2024)

The Space Between: On Folding, Symmetries and Sampling
by: Lewandowski, Michal, et al.
Published: (2025)

Elite Lanes: Evolutionary Generation of Realistic Small-Scale Road Networks
by: Morys-Magiera, Artur, et al.
Published: (2026)

Decoding the decoder: Contextual sequence-to-sequence modeling for intracortical speech decoding
by: Olak, Michal, et al.
Published: (2026)

Adaptive Estimation of the Number of Algorithm Runs in Stochastic Optimization
by: Eftimov, Tome, et al.
Published: (2025)

Domain-specific or Uncertainty-aware models: Does it really make a difference for biomedical text classification?
by: Sinha, Aman, et al.
Published: (2024)

Were You Helpful -- Predicting Helpful Votes from Amazon Reviews
by: Kirimlioglu, Emin, et al.
Published: (2024)

Sampling in CMA-ES: Low Numbers of Low Discrepancy Points
by: de Nobel, Jacob, et al.
Published: (2024)

On the Notion that Language Models Reason
by: Højer, Bertram
Published: (2025)

On Space Folds of ReLU Neural Networks
by: Lewandowski, Michal, et al.
Published: (2025)

A Theoretical Perspective on Why Stochastic Population Update Needs an Archive in Evolutionary Multi-objective Optimization
by: Ren, Shengjie, et al.
Published: (2025)

Automated Placement of Analog Integrated Circuits using Priority-based Constructive Heuristic
by: Grus, Josef, et al.
Published: (2024)

Should Under-parameterized Student Networks Copy or Average Teacher Weights?
by: Şimşek, Berfin, et al.
Published: (2023)

CantorNet: A Sandbox for Testing Geometrical and Topological Complexity Measures
by: Lewandowski, Michal, et al.
Published: (2024)

Evolutionary Generation of Random Surreal Numbers for Benchmarking
by: Roughan, Matthew
Published: (2025)

A Scalable Benchmark Test Suite for Dynamic Multi-Objective Optimization with a Changing Number of Objectives
by: Shang, Ke, et al.
Published: (2026)

A Multi-Branched Radial Basis Network Approach to Predicting Complex Chaotic Behaviours
by: Sinha, Aarush
Published: (2024)