arXiv AI
Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 17
SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models
arXiv:2605. 25420v2 Announce Type: replace-cross Abstract: Large language model safety evaluation remains heavily English-centered, leaving low-resource languages under-measured even when models are deployed globally.
arXiv AI
Aug 25
Redteaming Leading Arabic LLMs with ASAS
arXiv:2608.21985v1 Announce Type: new Abstract: As the adoption of large language models (LLMs) grows in Arabic-speaking regions, ensuring their safety and cultural alignment is increasingly critical...
arXiv AI
2d ago
Aligning Large Language Models for Safety in African Languages: A Case Study of Hausa
arXiv:2610.37245v1 Announce Type: cross Abstract: Safety alignment research for large language models (LLMs) remains concentrated on high-resource languages, leaving open how existing alignment metho...
arXiv AI
Sep 30
SalamahBench: Dialect and Category Level Safety Evaluation of Arabic Language Models
arXiv:2603.04410v3 Announce Type: replace-cross Abstract: While different stakeholders are trying to leverage Arabic Language Models (ALMs), safety alignment in ALMs remains largely underexplored, hi...
arXiv AI
Sep 15
From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions
arXiv:2603.13359v2 Announce Type: replace Abstract: Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusa...
arXiv Computation and Language
Sep 16
Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language Models
arXiv:2609.16006v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly serve users whose expectations are shaped by their cultural context, yet most cultural evaluations test wha...