No article text was recorded for this version.
cross-lingual safety disparity
Version 1 of 1291 papers673 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Tongue-Tied: Breaking LLMs Safety Through New Language Learning
- Blog: Low-Resource Languages Jailbreak GPT-4
- Blog: A Framework to Assess Multilingual Vulnerabilities of LLMs
- Blog: Qorǵau: Evaluating Safety in Kazakh-Russian Bilingual Contexts
- Blog: CSRT: Evaluation and Analysis of LLMs using Code-Switching Red-Teaming Dataset
- Blog: Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture
- Blog: The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts
- Blog: Multilingual Jailbreak Challenges in Large Language Models
- Blog: All Languages Matter: On the Multilingual Safety of Large Language Models
- Blog: The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts
- Blog: Multilingual Blending: Large Language Model Safety Alignment Evaluation with Language Mixture
- Blog: Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety
- Blog: A Framework to Assess Multilingual Vulnerabilities of LLMs
- Blog: MPO: Multilingual Safety Alignment via Reward Gap Optimization
- Blog: Multilingual Jailbreak Challenges in Large Language Models
- Blog: Benchmarking LLM Guardrails in Handling Multilingual Toxicity
- Blog: Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore’s Low-Resource Languages
- Blog: Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding
- Blog: Rainbow-Teaming for the Polish Language: A Reproducibility Study
- Blog: Qorgau: Evaluating LLM Safety in Kazakh-Russian Bilingual Contexts
- Blog: AraSafe: Benchmarking Safety in Arabic LLMs
- Blog: Multilingual Safety Alignment via Representation-Space Separability
- Blog: All Languages Matter: On the Multilingual Safety of LLMs
- Blog: IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages
- Blog: Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons
- Blog: Jailbreaking and Mitigation of Vulnerabilities in Large Language Models
- Blog: Multi-lingual Multi-turn Automated Red Teaming for LLMs
- Blog: $PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models
- Blog: Beyond Model Jailbreak: Systematic Dissection of the "Ten DeadlySins" in Embodied Intelligence
- Blog: LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
- Blog: Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages
- Blog: A First Look at GPT Apps: Landscape and Vulnerability
- Blog: XTRUST: On the Multilingual Trustworthiness of Large Language Models
- Blog: Multilingual Jailbreak Challenges in Large Language Models
- Blog: LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Models
- Blog: Comprehensive Assessment of Toxicity in ChatGPT
- Blog: Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge
- Blog: Benchmarking adversarial robustness to bias elicitation in large language models: scalable automated assessment with LLM-as-a-judge
- Blog: Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models
- Blog: Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking
- Blog: A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
- Blog: LLM Scheming Inversely Scales with Pretraining Language Coverage
- Blog: Delving into Multilingual Ethical Bias: The MSQAD with Statistical Hypothesis Tests for Large Language Models
- Blog: Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs
- Blog: LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps
- Blog: RabakBench: Scaling Human Annotations to Construct Localized Multilingual Safety Benchmarks for Low-Resource Languages
- Blog: Jailbreak Attacks and Defenses Against Large Language Models: A Survey
- Blog: Comprehensive Evaluation of ChatGPT Reliability Through Multilingual Inquiries
- Blog: Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation
- Blog: Evaluating and Mitigating Linguistic Discrimination in Large Language Models
- Blog: The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models
- Blog: S-Eval: Automatic and Adaptive Test Generation for Benchmarking Safety Evaluation of Large Language Models
- Blog: Refusal Direction is Universal Across Safety-Aligned Languages
- Blog: Consistency in Language Models: Current Landscape, Challenges, and Future Directions
- Blog: Transferring Troubles: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
- Blog: Large Language Model Adversarial Landscape Through the Lens of Attack Objectives
- Blog: Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings
- Blog: Low-Resource Languages Jailbreak GPT-4
- Blog: SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
- Blog: Understanding Catastrophic Forgetting in Language Models via Implicit Inference
Showing 60 of 291 papers.
History & citation
Current · Permanent link
- Cross-Lingual Safety Transfer in Large Language Models merged into this direction (50% overlap)
- This direction split from Cross-Lingual Safety Gaps in Large Language Models (88% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_lingual_safety_disparity_3241fe82,
title = {cross-lingual safety disparity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-lingual-safety-disparity/rdr_3241fe82def745a89e7629381e21a306},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_cross_lingual_safety_disparity_3241fe82_v1,
title = {cross-lingual safety disparity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-lingual-safety-disparity/rdr_3241fe82def745a89e7629381e21a306/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}