·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning3h◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks3h◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts3h◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning3h◆FrontierChallenge: Evaluating Scientific Workflow Completion3h◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier3h◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising3h◆Strangers to Themselves: What Language Models Say About Themselves Is Generic3h◆Omni Interaction Agent Technical Report3h◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification3h◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability3h◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization3h◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding3h◆Tracing Computation Density in LLMs3h◆Cultural Binding Heads in Language Models3h◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training3h◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models3h◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning3h◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection3h◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation3h◆Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning3h◆Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks3h◆Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts3h◆In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning3h◆FrontierChallenge: Evaluating Scientific Workflow Completion3h◆IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier3h◆AgenticGen: Reward-Guided Agentic Video Generation for Advertising3h◆Strangers to Themselves: What Language Models Say About Themselves Is Generic3h◆Omni Interaction Agent Technical Report3h◆CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification3h◆Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability3h◆Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization3h◆RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding3h◆Tracing Computation Density in LLMs3h◆Cultural Binding Heads in Language Models3h◆Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training3h◆Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models3h◆Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning3h◆'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection3h◆DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation3h◆
News/'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection
arxiv
PublishedSeptember 11, 2026 at 4:00 AM
—neutral

'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2608.24191v2 Announce Type: replace-cross Abstract: Urdu, the world's tenth most spoken language with 246 million speakers, remains almost entirely absent from mainstream LLM safety evaluation and nine years of WOAH proceedings. To investigate whether this absence has measurable consequences f

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivBringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning3harxivSubagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks3harxivDistribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts3harxivIn RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning3h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews