Imagen de Portada

Lost in Localization: Building RabakBench with Human-in-the-Loop Validation to Measure Multilingual Safety Gaps

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chua, Gabriel, Tan, Leanne, Ge, Ziyu, Lee, Roy Ka-Wei
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators
por: Tan, Leanne, et al.
Publicado: (2025)

Toxicity-Aware Few-Shot Prompting for Low-Resource Singlish Translation
por: Ge, Ziyu, et al.
Publicado: (2025)

Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning
por: Hwang, Jaedong, et al.
Publicado: (2025)

Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models
por: Luo, Zheng, et al.
Publicado: (2026)

MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control
por: Lee, Juyong, et al.
Publicado: (2024)

MPO: Multilingual Safety Alignment via Reward Gap Optimization
por: Zhao, Weixiang, et al.
Publicado: (2025)

Contrastive Token-level Explanations for Graph-based Rumour Detection
por: Chin, Daniel Wai Kit, et al.
Publicado: (2025)

Multilingual Safety Alignment via Self-Distillation
por: Qin, Ruiyang, et al.
Publicado: (2026)

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
por: Li, Junjie, et al.
Publicado: (2026)

The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It
por: Yong, Zheng-Xin, et al.
Publicado: (2025)

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

InstructAV: Instruction Fine-tuning Large Language Models for Authorship Verification
por: Hu, Yujia, et al.
Publicado: (2024)

LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs
por: Zhou, Yujun, et al.
Publicado: (2024)

Safe at the Margins: A General Approach to Safety Alignment in Low-Resource English Languages -- A Singlish Case Study
por: Lim, Isaac, et al.
Publicado: (2025)

LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs
por: Wu, Yuhao, et al.
Publicado: (2024)

Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance
por: Zheng, Weihua, et al.
Publicado: (2026)

M-RewardBench: Evaluating Reward Models in Multilingual Settings
por: Gureja, Srishti, et al.
Publicado: (2024)

Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs
por: Ge, Ziyu, et al.
Publicado: (2025)

Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
por: Bu, Yuyan, et al.
Publicado: (2026)

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures
por: Gringras, David
Publicado: (2026)

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
por: Wu, Yuhao, et al.
Publicado: (2025)

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models
por: Chua, Lynn, et al.
Publicado: (2024)

Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages
por: Hu, Yujia, et al.
Publicado: (2025)

MOSLD-Bench: Multilingual Open-Set Learning and Discovery Benchmark for Text Categorization
por: Costache, Adriana-Valentina, et al.
Publicado: (2026)

Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models
por: Ok, Hyunjong, et al.
Publicado: (2026)

Building a Few-Shot Cross-Domain Multilingual NLU Model for Customer Care
por: Kumar, Saurabh, et al.
Publicado: (2025)

Building Multilingual Datasets for Predicting Mental Health Severity through LLMs: Prospects and Challenges
por: Skianis, Konstantinos, et al.
Publicado: (2024)

Bridging the Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs
por: Kumar, Somnath, et al.
Publicado: (2024)

Building from Scratch: A Multi-Agent Framework with Human-in-the-Loop for Multilingual Legal Terminology Mapping
por: Meng, Lingyi, et al.
Publicado: (2025)

QueryBuilder: Human-in-the-Loop Query Development for Information Retrieval
por: Kandula, Hemanth, et al.
Publicado: (2024)

ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases
por: Zhong, Ziqian, et al.
Publicado: (2025)

The Proxy Presumption: From Semantic Embeddings to Valid Social Measures
por: Li, Baishi, et al.
Publicado: (2026)

CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications
por: Joshi, Raviraj, et al.
Publicado: (2025)

Interpreting Bias in Large Language Models: A Feature-Based Approach
por: Prakash, Nirmalendu, et al.
Publicado: (2024)

CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation
por: Chen, Tong, et al.
Publicado: (2024)

On the Calibration of Multilingual Question Answering LLMs
por: Yang, Yahan, et al.
Publicado: (2023)

Pretrained Multilingual Transformers Reveal Quantitative Distance Between Human Languages
por: Zhao, Yue, et al.
Publicado: (2026)

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
por: Jin, Chang, et al.
Publicado: (2026)

Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data
por: Kwak, Minseo, et al.
Publicado: (2026)

MinorBench: A hand-built benchmark for content-based risks for children
por: Khoo, Shaun, et al.
Publicado: (2025)