Cover Image

Why Do Safety Guardrails Degrade Across Languages?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Max, Patel, Ameen, Truong, Sang T., Koyejo, Sanmi
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reliable and Efficient Amortized Model-based Evaluation
by: Truong, Sang, et al.
Published: (2025)

Noise Injection Systemically Degrades Large Language Model Safety Guardrails
by: Shahani, Prithviraj Singh, et al.
Published: (2025)

Logits are All We Need to Adapt Closed Models
by: Hiranandani, Gaurush, et al.
Published: (2025)

Extracting books from production language models
by: Ahmed, Ahmed, et al.
Published: (2026)

From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
by: Zhou, Zhanke, et al.
Published: (2025)

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
by: Schaeffer, Rylan, et al.
Published: (2024)

Fantastic Bugs and Where to Find Them in AI Benchmarks
by: Truong, Sang, et al.
Published: (2025)

Investigating Data Contamination for Pre-training Language Models
by: Jiang, Minhao, et al.
Published: (2024)

UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models
by: Oh, Sejoon, et al.
Published: (2024)

Building a Domain-specific Guardrail Model in Production
by: Niknazar, Mohammad, et al.
Published: (2024)

Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Bounds
by: Chen, Edward, et al.
Published: (2025)

Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation
by: Gueorguieva, Anna-Maria, et al.
Published: (2025)

ZIP-FIT: Embedding-Free Data Selection via Compression-Based Alignment
by: Obbad, Elyas, et al.
Published: (2024)

Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training
by: Ilin, Aleksei, et al.
Published: (2025)

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment
by: Krishna, Kundan, et al.
Published: (2025)

The Sound of Syntax: Finetuning and Comprehensive Evaluation of Language Models for Speech Pathology
by: Patel, Fagun, et al.
Published: (2025)

Lean-ing on Quality: How High-Quality Data Beats Diverse Multilingual Data in AutoFormalization
by: Chan, Willy, et al.
Published: (2025)

Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data
by: Miranda, Brando, et al.
Published: (2023)

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
by: Liu, Dongrui, et al.
Published: (2026)

Quantifying the Importance of Data Alignment in Downstream Model Performance
by: Chawla, Krrish, et al.
Published: (2025)

Language Models Use Trigonometry to Do Addition
by: Kantamneni, Subhash, et al.
Published: (2025)

Questionnaire Responses Do not Capture the Safety of AI Agents
by: Hellrigel-Holderbaum, Max, et al.
Published: (2026)

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models
by: Liu, Qin, et al.
Published: (2024)

Why Larger Language Models Do In-context Learning Differently?
by: Shi, Zhenmei, et al.
Published: (2024)

Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models
by: Park, Jinyoung, et al.
Published: (2023)

Is Pre-training Truly Better Than Meta-Learning?
by: Miranda, Brando, et al.
Published: (2023)

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
by: Liu, Ken Ziyu, et al.
Published: (2025)

Parameter-Efficient Fine-Tuning for Low-Resource Languages: A Comparative Study of LLMs for Bengali Hate Speech Detection
by: Islam, Akif, et al.
Published: (2025)

Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?
by: Kang, Deokhyung, et al.
Published: (2025)

Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing
by: Neill, James O', et al.
Published: (2025)

KGGen: Extracting Knowledge Graphs from Plain Text with Language Models
by: Mo, Belinda, et al.
Published: (2025)

UQ: Assessing Language Models on Unsolved Questions
by: Nie, Fan, et al.
Published: (2025)

Discovering Implicit Large Language Model Alignment Objectives
by: Chen, Edward, et al.
Published: (2026)

Best-of-N Jailbreaking
by: Hughes, John, et al.
Published: (2024)

LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models
by: Elesedy, Hayder, et al.
Published: (2024)

Crossing Linguistic Horizons: Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models
by: Truong, Sang T., et al.
Published: (2024)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States
by: Sun, Yu, et al.
Published: (2024)

SafePred: A Predictive Guardrail for Computer-Using Agents via World Models
by: Chen, Yurun, et al.
Published: (2026)

Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
by: Huang, Yue, et al.
Published: (2025)

In-Situ Behavioral Evaluation for LLM Fairness, Not Standardized-Test Scores
by: Tang, Zeyu, et al.
Published: (2026)