arXiv AI
AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 2
Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment
arXiv:2606. 00369v1 Announce Type: cross Abstract: Safe global deployment of AI models requires alignment with human values that vary across cultures.
arXiv Computation and Language
Sep 22
Tutoring Large Language Models to be Domain-adaptive, Precise and Safe
arXiv:2609.23071v1 Announce Type: cross Abstract: This thesis proposes a framework for "responsible intelligence" to address AI's critical challenges in safety, ethics, and cultural sensitivity. It a...
arXiv Computation and Language
Aug 31
CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia
arXiv:2608.28405v1 Announce Type: new Abstract: Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common...
arXiv Computation and Language
4d ago
KSAFE-MM: A Multimodal Safety Benchmark via Localized Contextualization for Korean Cultural Risks
arXiv:2605.28013v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vi...
Hugging Face Trending Papers
Aug 11
The Illusion of Cross-Lingual Safety in Low-Resource Languages
Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings. However, this assumption remains underexplored and exposes a vulnerability in low-resource languages.
Hugging Face Trending Papers
Sep 3
IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks
IndicSafeEval is a new evaluation framework that tests the safety robustness of large language models against persuasion-based jailbreak attacks in Indian languages. The benchmark covers ten safety-critical content categories, six persuasive strategies, and four languages—Hindi, Bengali, Marathi, and Punjabi—producing 7,200 adversarial prompts. Experiments show that model safety varies significantly across languages, prompt styles, and risk categories, highlighting gaps in current English-centric safety assessments.