2026-09-21T00:11:55.984Z
- publishedAt:
2026-01-01T00:00:00.000Z→ Not provided
SOURCE-LINKED INTELLIGENCE
Code-Switching as a Safety Failure Mode in Large Language Models: An Empirical Study of Roman Urdu across English, Mixed, and Transliteration-Only Inputs
Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- ACL Anthology
- OpenAlex research metadata · 2026-01-01T00:00:00.000Z
ACL Anthology and the credited paper authors. Bibliographic metadata only; abstracts and full papers are excluded. Third-party materials retain their respective rights.
License: ACL Anthology usage policy (metadata)
First collected: 2026-09-19T23:01:46.082Z. This is not the publication date.
Observed changes
AIIC observation times, not verified publisher revision times. Up to eight recent revisions.
2026-09-20T23:22:28.549Z
- publishedAt:
Not provided→ 2026-01-01T00:00:00.000Z
Research metadata
OpenAlex record ↗ · Metadata licensed CC0; paper rights are separate.
- Citations reported by OpenAlex
- 0
- Authors
- Waleed Jamil; Saima Rafi
- Affiliations
- Edinburgh Napier University (GB)
- Topic
- Multilingual Education and Policy
- Publication type
- conference-paper
- Retraction flag reported by OpenAlex
- Not flagged
Citation count and retraction flag reported by OpenAlex. Citations are not a quality score; affiliation countries are not study locations.