From Normative Frameworks to Alignment Data: Constructing and Evaluating SFT and Preference Data

The paper presents an expert-driven method for turning normative principles—specifically Islamic ethical, theological, and jurisprudential traditions—into alignment data for language models. Over a year, seven experts curated 2.8K supervised fine-tuning examples and 5.4K preference pairs in Arabic-English, then evaluated models trained on these datasets. Experiments show that models trained with the curated SFT data outperform a baseline in expert judgments, while adding preference data yields a smaller, non-significant improvement.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

• llms
• fine-tuning
• benchmarks
• safety