No article text was recorded for this version.
localized safety alignment
Version 2 of 291 papers137 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Qorǵau: Evaluating Safety in Kazakh-Russian Bilingual Contexts
- Blog: Qorgau: Evaluating LLM Safety in Kazakh-Russian Bilingual Contexts
- Blog: CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications
- Blog: SEA-SafeguardBench: Evaluating AI Safety in SEA Languages and Cultures
- Blog: SeaLLMs - Large Language Models for Southeast Asia
- Blog: FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypes
- Blog: AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications
- Blog: SeaExam and SeaBench: Benchmarking LLMs with Local Multilingual Questions in Southeast Asia
- Blog: SeaExam and SeaBench: Benchmarking LLMs with Local Multilingual Questions in Southeast Asia
- Blog: Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models
- Blog: FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypes
- Blog: SESGO: Spanish Evaluation of Stereotypical Generative Outputs
- Blog: LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs
- Blog: From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models
- Blog: Exploring Inherent Biases in LLMs within Korean Social Context: A Comparative Analysis of ChatGPT and GPT-4
- Blog: AssurAI: Experience with Constructing Korean Socio-cultural Datasets to Discover Potential Risks of Generative AI
- Blog: The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm
- Blog: KoSBI: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Applications
- Blog: FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models
- Blog: Beyond Uniform Criteria: Scenario-Adaptive Multi-Dimensional Jailbreak Evaluation
- Blog: A Chinese Dataset for Evaluating the Safeguards in Large Language Models
- Blog: JailBench: A Comprehensive Chinese Security Assessment Benchmark for Large Language Models
- Blog: Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models
- Blog: Arabic Dataset for LLM Safeguard Evaluation
- Blog: SafeWorld: Geo-Diverse Safety Alignment
- Blog: "They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations
- Blog: Multimodal Cultural Safety: Evaluation Frameworks and Alignment Strategies
- Blog: Framing Political Bias in Multilingual LLMs Across Pakistani Languages
- Blog: Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment
- Blog: Sherkala-Chat: Building a State-of-the-Art LLM for Kazakh in a Moderately Resourced Setting
- Blog: Sherkala-Chat: Building a State-of-the-Art LLM for Kazakh in a Moderately Resourced Setting
- Blog: Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation
- Blog: IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages
- Blog: The Colorful Future of LLMs: Evaluating and Improving LLMs as Emotional Supporters for Queer Youth
- Blog: RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?
- Blog: AssurAI: Experience with Constructing Korean Socio-cultural Datasets to Discover Potential Risks of Generative AI
- Blog: KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application
- Blog: CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation
- Blog: Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
- Blog: Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings
- Blog: Krikri: Advancing Open Large Language Models for Greek
- Blog: Exploring Human Perceptions of AI Responses: Insights from a Mixed-Methods Study on Risk Mitigation in Generative Models
- Blog: LionGuard: A Contextualized Moderation Classifier to Tackle Localized Unsafe Content
- Blog: SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Facts
- Blog: Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk
- Blog: Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactions
- Blog: SeaLLMs - Large Language Models for Southeast Asia
- Blog: Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs
- Blog: Arabic Dataset for LLM Safeguard Evaluation
- Blog: Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect
- Blog: Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages
- Blog: SOSBENCH: Benchmarking Safety Alignment on Six Scientific Domains
- Blog: Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons
- Blog: WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models
- Blog: SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration
- Blog: Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings
- Blog: Exploring Safety Alignment Evaluation of LLMs in Chinese Mental Health Dialogues via LLM-as-Judge
- Blog: Taxonomy and Analysis of Sensitive User Queries in Generative AI Search System
- Blog: SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions
- Blog: SEA-HELM: Southeast Asian Holistic Evaluation of Language Models
Showing 60 of 91 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_localized_safety_alignment_3cb8c189,
title = {localized safety alignment},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/localized-safety-alignment/rdr_3cb8c189c91b474b836722f591038795},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_localized_safety_alignment_3cb8c189_v2,
title = {localized safety alignment},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/localized-safety-alignment/rdr_3cb8c189c91b474b836722f591038795/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}