$Copertina$

MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Kaixuan, Guo, Jiacheng, Li, Zihao, Ji, Xiang, Ge, Jiawei, Li, Wenzhe, Guo, Yingqing, Cai, Tianle, Yuan, Hui, Wang, Runzhe, Wu, Yue, Yin, Ming, Tang, Shange, Huang, Yangsibo, Jin, Chi, Chen, Xinyun, Zhang, Chiyuan, Wang, Mengdi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
di: Huang, Kaixuan, et al.
Pubblicazione: (2024)

Principled Out-of-Distribution Generalization via Simplicity
di: Ge, Jiawei, et al.
Pubblicazione: (2025)

Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?
di: Hu, Yijie, et al.
Pubblicazione: (2025)

MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contexts
di: Wang, Peijie, et al.
Pubblicazione: (2025)

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
di: Fang, Hao, et al.
Pubblicazione: (2024)

Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games
di: Ge, Jiawei, et al.
Pubblicazione: (2024)

On the Role of Preference Variance in Preference Optimization
di: Guo, Jiacheng, et al.
Pubblicazione: (2025)

Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models
di: Guo, Yingqing, et al.
Pubblicazione: (2025)

On Memorization of Large Language Models in Logical Reasoning
di: Xie, Chulin, et al.
Pubblicazione: (2024)

Understanding the Ability of LLMs to Handle Character-Level Perturbation
di: Zhuo, Anyuan, et al.
Pubblicazione: (2025)

Assessing the Ability of Neural TTS Systems to Model Consonant-Induced F0 Perturbation
di: Yang, Tianle, et al.
Pubblicazione: (2026)

Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations
di: Hu, Hanjiang, et al.
Pubblicazione: (2023)

Temporal Consistency for LLM Reasoning Process Error Identification
di: Guo, Jiacheng, et al.
Pubblicazione: (2025)

Visual Perturbation and Adaptive Hard Negative Contrastive Learning for Compositional Reasoning in Vision-Language Models
di: Huang, Xin, et al.
Pubblicazione: (2025)

Probing the Robustness of Large Language Models Safety to Latent Perturbations
di: Gu, Tianle, et al.
Pubblicazione: (2025)

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
di: Wei, Boyi, et al.
Pubblicazione: (2024)

Contrasting Adversarial Perturbations: The Space of Harmless Perturbations
di: Chen, Lu, et al.
Pubblicazione: (2024)

Metric Reconstruction and Second Order Perturbation for Generic Spherically Symmetric spacetime
di: Guo, Rong-Zhen, et al.
Pubblicazione: (2026)

Quantifying Cross-Modality Memorization in Vision-Language Models
di: Wen, Yuxin, et al.
Pubblicazione: (2025)

Gradient Guidance for Diffusion Models: An Optimization Perspective
di: Guo, Yingqing, et al.
Pubblicazione: (2024)

MM-MATH: Advancing Multimodal Math Evaluation with Process Evaluation and Fine-grained Classification
di: Sun, Kai, et al.
Pubblicazione: (2024)

Is Elo Rating Reliable? A Study Under Model Misspecification
di: Tang, Shange, et al.
Pubblicazione: (2025)

MATH-PT: A Math Reasoning Benchmark for European and Brazilian Portuguese
di: Teixeira, Tiago, et al.
Pubblicazione: (2026)

AGNNCert: Defending Graph Neural Networks against Arbitrary Perturbations with Deterministic Certification
di: Li, Jiate, et al.
Pubblicazione: (2025)

Diffusion Model for Data-Driven Black-Box Optimization
di: Li, Zihao, et al.
Pubblicazione: (2024)

EmoRAG: Evaluating RAG Robustness to Symbolic Perturbations
di: Zhou, Xinyun, et al.
Pubblicazione: (2025)

A Theoretical Perspective for Speculative Decoding Algorithm
di: Yin, Ming, et al.
Pubblicazione: (2024)

A Note on Eigenvalues of Perturbed Hermitian Matrices
di: Li, Chi-Kwong, et al.
Pubblicazione: (2025)

Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
di: Lu, Rui, et al.
Pubblicazione: (2025)

LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction
di: Zhang, Jensen, et al.
Pubblicazione: (2025)

Evaluating Copyright Takedown Methods for Language Models
di: Wei, Boyi, et al.
Pubblicazione: (2024)

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
di: Li, Jiate, et al.
Pubblicazione: (2025)

Gradient Perturbation: Learning to Perturb Gradients for Adaptive Training
di: Li, Hua
Pubblicazione: (2026)

Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations
di: Li, Jiate, et al.
Pubblicazione: (2025)

Robust Federated Learning against Model Perturbation in Edge Networks
di: Jin, Dongzi, et al.
Pubblicazione: (2025)

PerturbDiff: Functional Diffusion for Single-Cell Perturbation Modeling
di: Yuan, Xinyu, et al.
Pubblicazione: (2026)

Synthesis of Liquid Polysilazoxanes for SiOCN Ceramics With Adjustable Composition and High‐Temperature Properties
di: Chiyuan Wang, et al.
Pubblicazione: (2025)

Rank Resilience of Pattern Matrices against Structured Perturbations with Applications
di: Zhang, Yuan, et al.
Pubblicazione: (2021)

Detecting Adversarial Data using Perturbation Forgery
di: Wang, Qian, et al.
Pubblicazione: (2024)

Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration
di: Huang, Langlin, et al.
Pubblicazione: (2026)