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

arXiv:2609.35201 · cs.CL, cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Alignment — 64× in this paper · explained in 1 episode
• Benchmark — 14× in this paper · explained in 2 episodes
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Consistency — 6× in this paper · explained in 3 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Pairwise Comparisons — 5× in this paper · explained in 2 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Benchmarking — 4× in this paper · explained in 3 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Direct Preference Optimization — 3× in this paper
• Failure Modes — 3× in this paper · explained in 3 episodes
• Alignment Problem — 2× in this paper · explained in 1 episode
• Direct Preference Optimization (DPO) — 2× in this paper · explained in 9 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 2× in this paper · explained in 8 episodes
• AI Alignment — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Arabic Cultural Value Alignment — 1× in this paper
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Fanar 2.0: Arabic Generative AI Stack
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• Constitutional AI: Harmlessness from AI Feedback
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Scalable agent alignment via reward modeling: a research direction
• A Roadmap to Pluralistic Alignment
• Gemma 4 Technical Report
• Scopes of Alignment
• Finetuned Language Models Are Zero-Shot Learners

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering