Enhancing Robustness of Autoregressive Language Models against Orthographic Attacks via Pixel-based Approach

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Han, Lan, Jian, Liu, Yihong, Schütze, Hinrich, Seidl, Thomas
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Relational Linearity is a Predictor of Hallucinations
by: Lu, Yuetian, et al.
Published: (2026)

Exploring the Role of Transliteration in In-Context Learning for Low-resource Languages Written in Non-Latin Scripts
by: Ma, Chunlan, et al.
Published: (2024)

MoSECroT: Model Stitching with Static Word Embeddings for Crosslingual Zero-shot Transfer
by: Ye, Haotian, et al.
Published: (2024)

GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages
by: Kargaran, Amir Hossein, et al.
Published: (2024)

Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation
by: Wang, Qianli, et al.
Published: (2026)

GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network
by: Yuan, Shuzhou, et al.
Published: (2024)

A Federated Approach to Few-Shot Hate Speech Detection for Marginalized Communities
by: Ye, Haotian, et al.
Published: (2024)

Evaluating Contextually Mediated Factual Recall in Multilingual Large Language Models
by: Liu, Yihong, et al.
Published: (2026)

Derivational Morphology Reveals Analogical Generalization in Large Language Models
by: Hofmann, Valentin, et al.
Published: (2024)

MenuCraft: Interactive Menu System Design with Large Language Models
by: Kargaran, Amir Hossein, et al.
Published: (2023)

Simulated Annealing Enhances Theory-of-Mind Reasoning in Autoregressive Language Models
by: Hu, Xucong, et al.
Published: (2026)

Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment
by: Xhelili, Orgest, et al.
Published: (2024)

Modeling Orthographic Variation Improves NLP Performance for Nigerian Pidgin
by: Lin, Pin-Jie, et al.
Published: (2024)

Hidden State Poisoning Attacks against Mamba-based Language Models
by: Mercier, Alexandre Le, et al.
Published: (2026)

HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization
by: Özeren, Enes, et al.
Published: (2025)

MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions
by: Köksal, Abdullatif, et al.
Published: (2024)

Do We Still Need Humans in the Loop? Comparing Human and LLM Annotation in Active Learning for Hostility Detection
by: Hakimi, Ahmad Dawar, et al.
Published: (2026)

ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge
by: Taghavi, Zeinab Sadat, et al.
Published: (2025)

Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks
by: Mu, Lin, et al.
Published: (2025)

Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
by: Röttger, Paul, et al.
Published: (2024)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
by: Jiang, Tanqiu, et al.
Published: (2024)

Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn't
by: Taguchi, Chihiro, et al.
Published: (2024)

Unveiling the "Fairness Seesaw": Discovering and Mitigating Gender and Race Bias in Vision-Language Models
by: Lan, Jian, et al.
Published: (2025)

MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment
by: Kargaran, Amir Hossein, et al.
Published: (2024)

LINGOLY-TOO: Disentangling Reasoning from Knowledge with Templatised Orthographic Obfuscation
by: Khouja, Jude, et al.
Published: (2025)

LongForm: Effective Instruction Tuning with Reverse Instructions
by: Köksal, Abdullatif, et al.
Published: (2023)

CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation
by: Ziegler, Ingo, et al.
Published: (2024)

Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotations
by: Pan, Linrong, et al.
Published: (2025)

Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors
by: Zhao, Raoyuan, et al.
Published: (2025)

Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding
by: Feng, Qi, et al.
Published: (2025)

Beyond Input Understanding: Diagnosing Multilingual Mathematical Reasoning with Directed Acyclic Trace Graphs
by: Zhang, Jiaqiao, et al.
Published: (2026)

How Programming Concepts and Neurons Are Shared in Code Language Models
by: Kargaran, Amir Hossein, et al.
Published: (2025)

Semantic Representation Attack against Aligned Large Language Models
by: Lian, Jiawei, et al.
Published: (2025)

TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models
by: Liu, Yihong, et al.
Published: (2024)

Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring
by: Mu, Honglin, et al.
Published: (2024)

TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data
by: Liu, Yihong, et al.
Published: (2024)

BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning
by: Nie, Ercong, et al.
Published: (2024)

Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders
by: Veitsman, Yana, et al.
Published: (2026)

DROJ: A Prompt-Driven Attack against Large Language Models
by: Hu, Leyang, et al.
Published: (2024)

Fast Adversarial Training against Textual Adversarial Attacks
by: Yang, Yichen, et al.
Published: (2024)