Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data

arXiv:2609.16532 · cs.CL · Submitted 2026-09-15 · Read on arXiv

cs.CL

Submitted: 2026-09-15

Updated: 2026-09-15

Comments: 23 pages, 3 figures, 13 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 38× in this paper · explained in 1 episode
• Benchmark — 18× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Data Augmentation — 4× in this paper · explained in 7 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Grounding — 3× in this paper · explained in 3 episodes
• Large Language Model (LLM) — 3× in this paper · explained in 3 episodes
• Regularization — 3× in this paper · explained in 3 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Additive Decomposition — 2× in this paper · explained in 1 episode
• Catastrophic Forgetting — 2× in this paper · explained in 5 episodes
• Direct Preference Optimization (DPO) — 2× in this paper · explained in 9 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Synthetic Data Generation — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• The Llama 3 Herd of Models
• The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features
• RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
• An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
• What Matters in Data for DPO?
• PASTA: A Paraphrasing And Self-Training Approach for Knowledge Updating in LLMs

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