Cover Image

The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	El-Shangiti, Ahmed Oumar, Hiraoka, Tatsuya, AlQuabeh, Hilal, Heinzerling, Benjamin, Inui, Kentaro
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Number Representations in LLMs: A Computational Parallel to Human Perception
by: AlquBoj, H. V., et al.
Published: (2025)

Monotonic Representation of Numeric Properties in Language Models
by: Heinzerling, Benjamin, et al.
Published: (2024)

Emergence of Primacy and Recency Effect in Mamba: A Mechanistic Point of View
by: Airlangga, Muhammad Cendekia, et al.
Published: (2025)

Mechanistic Insights into Grokking from the Embedding Layer
by: AlquBoj, H. V., et al.
Published: (2025)

Repetition Neurons: How Do Language Models Produce Repetitions?
by: Hiraoka, Tatsuya, et al.
Published: (2024)

Spelling-out is not Straightforward: LLMs' Capability of Tokenization from Token to Characters
by: Hiraoka, Tatsuya, et al.
Published: (2025)

Representational Analysis of Binding in Language Models
by: Dai, Qin, et al.
Published: (2024)

Cell-Based Representation of Relational Binding in Language Models
by: Dai, Qin, et al.
Published: (2026)

RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles
by: Nwadike, Munachiso, et al.
Published: (2025)

Linear Representations of Hierarchical Concepts in Language Models
by: Sakata, Masaki, et al.
Published: (2026)

Sycophancy Hides Linearly in the Attention Heads
by: Genadi, Rifo, et al.
Published: (2026)

TopK Language Models
by: Takahashi, Ryosuke, et al.
Published: (2025)

Uncovering the Spectral Bias in Diagonal State Space Models
by: Solozabal, Ruben, et al.
Published: (2025)

Arabic Automatic Story Generation with Large Language Models
by: El-Shangiti, Ahmed Oumar, et al.
Published: (2024)

Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge
by: Zhang, Ying, et al.
Published: (2025)

Understanding and Controlling Repetition Neurons and Induction Heads in In-Context Learning
by: Doan, Nhi Hoai, et al.
Published: (2025)

On Entity Identification in Language Models
by: Sakata, Masaki, et al.
Published: (2025)

ACORN: Aspect-wise Commonsense Reasoning Explanation Evaluation
by: Brassard, Ana, et al.
Published: (2024)

The Curse of Popularity: Popular Entities have Catastrophic Side Effects when Deleting Knowledge from Language Models
by: Takahashi, Ryosuke, et al.
Published: (2024)

Do LLMs Need to Think in One Language? Correlation between Latent Language and Task Performance
by: Ozaki, Shintaro, et al.
Published: (2025)

Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference
by: Kamoda, Go, et al.
Published: (2025)

Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki
by: Sasaki, Mutsumi, et al.
Published: (2025)

Limited Memory Online Gradient Descent for Kernelized Pairwise Learning with Dynamic Averaging
by: AlQuabeh, Hilal, et al.
Published: (2024)

Hidden Failures in Robustness: Why Supervised Uncertainty Quantification Needs Better Evaluation
by: Stacey, Joe, et al.
Published: (2026)

Knowledge of Pretrained Language Models on Surface Information of Tokens
by: Hiraoka, Tatsuya, et al.
Published: (2024)

Tokenization Preference for Human and Machine Learning Model: An Annotation Study
by: Hiraoka, Tatsuya, et al.
Published: (2023)

Rectifying Belief Space via Unlearning to Harness LLMs' Reasoning
by: Niwa, Ayana, et al.
Published: (2025)

How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencoders
by: Inaba, Tatsuro, et al.
Published: (2025)

Syntactic Learnability of Echo State Neural Language Models at Scale
by: Ueda, Ryo, et al.
Published: (2025)

First Heuristic Then Rational: Dynamic Use of Heuristics in Language Model Reasoning
by: Aoki, Yoichi, et al.
Published: (2024)

Large Language Models Are Human-Like Internally
by: Kuribayashi, Tatsuki, et al.
Published: (2025)

Bit-level BPE: Below the byte boundary
by: Moon, Sangwhan, et al.
Published: (2025)

A Large Collection of Model-generated Contradictory Responses for Consistency-aware Dialogue Systems
by: Sato, Shiki, et al.
Published: (2024)

Constrained Adversarial Perturbation
by: Nishad, Virendra, et al.
Published: (2025)

How Individual Traits and Language Styles Shape Preferences In Open-ended User-LLM Interaction: A Preliminary Study
by: Chevi, Rendi, et al.
Published: (2025)

LogiNumSynth: Synthesizing Joint Logical-Numerical Reasoning Problems for Language Models
by: Liu, Yiwei, et al.
Published: (2025)

MetaRuleGPT: Recursive Numerical Reasoning of Language Models Trained with Simple Rules
by: Chen, Kejie, et al.
Published: (2024)

Measuring AI Reasoning: A Guide for Researchers
by: Nwadike, Munachiso Samuel, et al.
Published: (2026)

Enhancing Numerical Reasoning with the Guidance of Reliable Reasoning Processes
by: Wang, Dingzirui, et al.
Published: (2024)

Investigating Numerical Translation with Large Language Models
by: Tang, Wei, et al.
Published: (2025)