Alignment at Pre-training! Towards Native Alignment for Arabic LLMs
This addresses alignment for Arabic LLMs, offering a novel approach that could benefit the Arabic LLM community, though it appears incremental in method.
The paper tackles the problem of aligning large language models by proposing native alignment during pre-training, specifically for Arabic LLMs, and releases open-source models that achieve state-of-the-art performance on benchmarks.
The alignment of large language models (LLMs) is critical for developing effective and safe language models. Traditional approaches focus on aligning models during the instruction tuning or reinforcement learning stages, referred to in this paper as `post alignment'. We argue that alignment during the pre-training phase, which we term `native alignment', warrants investigation. Native alignment aims to prevent unaligned content from the beginning, rather than relying on post-hoc processing. This approach leverages extensively aligned pre-training data to enhance the effectiveness and usability of pre-trained models. Our study specifically explores the application of native alignment in the context of Arabic LLMs. We conduct comprehensive experiments and ablation studies to evaluate the impact of native alignment on model performance and alignment stability. Additionally, we release open-source Arabic LLMs that demonstrate state-of-the-art performance on various benchmarks, providing significant benefits to the Arabic LLM community.