Skip to content
AI Atlas
PaperActive

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

arxiv.org/abs/2608.24191

Updated 52 min ago · first seen 11 Sept 2026

paper_01M294GQF8SKAS8PJRDNSXHM4P

Published
11 Sept 2026
T1 · 52 min ago
arXiv
2608.24191
T1 · 52 min ago
Category
cs.CL
T1 · 52 min ago

Abstract

-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 for content moderation reliability, five large language models, GPT-4o, Claude Sonnet 4.5, Gemini 2.5 Flash, Qwen-2.5, and Llama-3.1, were tested across six datasets spanning Nastaliq Urdu, Roman Urdu, English, and code-switched Urdu-English. Across the five Urdu-script datasets, label instability between original-script and English-translation classification ranged from 15.9% (Gemini 2.5 Flash) to 31.6% (Qwen-2.5), with a 'Missed-in-Urdu' rate, content flagged as harmful in English translation but passed as normal in the original script, ranging from 2.4% to 9.9% (median 4.3%). A complete enumeration of all 205 papers across nine ALW/WOAH editions via the ACL Anthology API confirms zero dedicated Urdu papers across the entire period. Results indicate that current LLMs provide uneven safety assurance across Urdu's script varieties, with smaller open-weight models showing substantially higher instability and missed-harm rates than frontier closed models.

Authors 4

Fawzia Zehra (Fuzzy), Kara-Isitt, Sonal Khosla, Stephen Swift

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Arxiv announce type
replace

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

arXiv id
2608.24191

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Categories
cs.CL, cs.AI

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Primary category
cs.CL

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 52 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

52 min ago

Conflicts

None