paper-with-me

Papers

Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding

2024-06-17 · Haneul Yoo, Yongjin Yang, Hwaran Lee

As large language models (LLMs) have advanced rapidly, concerns regarding their safety have become prominent. In this paper, we discover that code-switching in red-teaming queries can effectively elicit undesirable behaviors of LLMs, which are common practices in natural language. We introduce a simple yet effective framework, CSRT, to synthesize code-switching red-teaming queries and investigate the safety and multilingual understanding of LLMs comprehensively. Through extensive experiments with ten state-of-the-art LLMs and code-switching queries combining up to 10 languages, we demonstrate that the CSRT significantly outperforms existing multilingual red-teaming techniques, achieving 46.7% more attacks than standard attacks in English and being effective in conventional safety domains. We also examine the multilingual ability of those LLMs to generate and understand code-switching texts. Additionally, we validate the extensibility of the CSRT by generating code-switching attack prompts with monolingual data. We finally conduct detailed ablation studies exploring code-switching and propound unintended correlation between resource availability of languages and safety alignment in existing multilingual LLMs.

📄 PDF Abstract BibTeX arXiv:2406.15481

Code (1)

haneul-yoo/csrt 공식 구현

Tasks

16kLanguage ModellingRed TeamingSafety Alignment

Similar Papers 제목 키워드 기반

X-Guard: Multilingual Guard Agent for Content Moderation

2025-04-11 · Bibek Upadhayay, Vahid Behzadan, Ph. D

Large Language Models (LLMs) have rapidly become integral to numerous applications in critical domains where reliability is paramount. Despite significant advances in safety frameworks and guardrails, current protective …

RabakBench: Scaling Human Annotations to Construct Localized Multilingual Safety Benchmarks for Low-Resource Languages

2025-07-08 · Gabriel Chua, Leanne Tan, Ziyu Ge, Roy Ka-Wei Lee

Large language models (LLMs) and their safety classifiers often perform poorly on low-resource languages due to limited training data and evaluation benchmarks. This paper introduces RabakBench, a new multilingual safety…

Red Teaming

Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety

2026-07-11 · Chigozirim Ifebi, Brent Kong, Ayushi Mehrotra arxiv

Safety alignment in large language models remains brittle across languages: prompts reliably refused in English can elicit harmful compliance in non-English and low-resource settings. We introduce \textsc{Minionese}, a m…

Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages

2025-09-18 · Yujia Hu, Ming Shan Hee, Preslav Nakov, Roy Ka-Wei Lee arxiv

The advancement of Large Language Models (LLMs) has transformed natural language processing; however, their safety mechanisms remain under-explored in low-resource, multilingual settings. Here, we aim to bridge this gap.…

Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle

2024-07-18 · Emman Haider, Daniel Perez-Becker, Thomas Portet, Piyush Madan 외

Recent innovations in language model training have demonstrated that it is possible to create highly performant models that are small enough to run on a smartphone. As these models are deployed in an increasing number of…

BenchmarkingLanguage ModelingLanguage ModellingRed Teaming