Cover Image

Numerical Instability and Chaos: Quantifying the Unpredictability of Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Islam, Chashi Mahiul, Villarreal, Alan, Nishino, Mao, Salman, Shaeke, Liu, Xiuwen
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning Numerical Analysis
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems
by: Islam, Chashi Mahiul, et al.
Published: (2024)

Are Vision Transformer Representations Semantically Meaningful? A Case Study in Medical Imaging
by: Shams, Montasir, et al.
Published: (2025)

Adversarial Attacks on Large Language Models Using Regularized Relaxation
by: Chacko, Samuel Jacob, et al.
Published: (2024)

Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers
by: Islam, Chashi Mahiul, et al.
Published: (2025)

Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning
by: Islam, Chashi Mahiul, et al.
Published: (2025)

Intriguing Differences Between Zero-Shot and Systematic Evaluations of Vision-Language Transformer Models
by: Salman, Shaeke, et al.
Published: (2024)

Unaligning Everything: Or Aligning Any Text to Any Image in Multimodal Models
by: Salman, Shaeke, et al.
Published: (2024)

Intriguing Equivalence Structures of the Embedding Space of Vision Transformers
by: Salman, Shaeke, et al.
Published: (2024)

AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios
by: Huang, Zhongzhan, et al.
Published: (2023)

AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing
by: Du, Jianda, et al.
Published: (2026)

Online Pseudo-average Shifting Attention(PASA) for Robust Low-precision LLM Inference: Algorithms and Numerical Analysis
by: Cheng, Long, et al.
Published: (2025)

Core-Halo Decomposition: Decentralizing Large-Scale Fixed-Point Problems
by: Haixiang, et al.
Published: (2026)

Deep Learning-Enhanced Preconditioning for Efficient Conjugate Gradient Solvers in Large-Scale PDE Systems
by: Li, Rui, et al.
Published: (2024)

Numerical Error Analysis of Large Language Models
by: Budzinskiy, Stanislav, et al.
Published: (2025)

When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity
by: Chacko, Samuel Jacob, et al.
Published: (2026)

Defining Foundation Models for Computational Science: A Call for Clarity and Rigor
by: Choi, Youngsoo, et al.
Published: (2025)

Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration
by: Pourkamali-Anaraki, Farhad
Published: (2026)

PDE Generalization of In-Context Operator Networks: A Study on 1D Scalar Nonlinear Conservation Laws
by: Yang, Liu, et al.
Published: (2024)

DeepContour: A Hybrid Deep Learning Framework for Accelerating Generalized Eigenvalue Problem Solving via Efficient Contour Design
by: Chen, Yeqiu, et al.
Published: (2025)

DeepSeek on a Trip: Inducing Targeted Visual Hallucinations via Representation Vulnerabilities
by: Islam, Chashi Mahiul, et al.
Published: (2025)

When is a System Discoverable from Data? Discovery Requires Chaos
by: Shumaylov, Zakhar, et al.
Published: (2025)

KAN-GCN: Combining Kolmogorov-Arnold Network with Graph Convolution Network for an Accurate Ice Sheet Emulator
by: Liu, Zesheng, et al.
Published: (2025)

Graph Neural Network as Computationally Efficient Emulator of Ice-sheet and Sea-level System Model (ISSM)
by: Koo, Younghyun, et al.
Published: (2024)

Mitigating spectral bias for the multiscale operator learning
by: Liu, Xinliang, et al.
Published: (2022)

P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
by: Wang, Qi, et al.
Published: (2024)

Learning to Discover Iterative Spectral Algorithms
by: Liu, Zihang, et al.
Published: (2026)

A Mathematical Explanation of Transformers
by: Tai, Xue-Cheng, et al.
Published: (2025)

Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training
by: Li, Qinglun, et al.
Published: (2025)

Neural Operators with Localized Integral and Differential Kernels
by: Liu-Schiaffini, Miguel, et al.
Published: (2024)

Fractal Language Modelling by Universal Sequence Maps (USM)
by: Almeida, Jonas S, et al.
Published: (2025)

BWLer: Barycentric Weight Layer Elucidates a Precision-Conditioning Tradeoff for PINNs
by: Liu, Jerry, et al.
Published: (2025)

AlgoFormer: An Efficient Transformer Framework with Algorithmic Structures
by: Gao, Yihang, et al.
Published: (2024)

Intrinsic Numerical Robustness and Fault Tolerance in a Neuromorphic Algorithm for Scientific Computing
by: Theilman, Bradley H., et al.
Published: (2026)

Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning
by: Berner, Julius, et al.
Published: (2025)

A Practical Approach to Causal Inference over Time
by: Cinquini, Martina, et al.
Published: (2024)

A Mathematical Guide to Operator Learning
by: Boullé, Nicolas, et al.
Published: (2023)

Truncated Matrix Completion - An Empirical Study
by: Naik, Rishhabh, et al.
Published: (2025)

Random weights of DNNs and emergence of fixed points
by: Berlyand, L., et al.
Published: (2025)

Deriving Transformer Architectures as Implicit Multinomial Regression
by: Actor, Jonas A., et al.
Published: (2025)

Sparse $L^1$-Autoencoders for Scientific Data Compression
by: Chung, Matthias, et al.
Published: (2024)