GAW-PO: Preference Optimization with Gradient-Aligned Token Weights

arXiv:2610.01511 · cs.CL · Submitted 2026-10-01 · Read on arXiv

cs.CL

Submitted: 2026-10-01

Updated: 2026-10-02

Terminology

• Benchmark — 28× in this paper · explained in 2 episodes
• Alignment — 27× in this paper · explained in 1 episode
• Alignment Scores — 9× in this paper · explained in 1 episode
• Direct Preference Optimization — 9× in this paper
• Regularization — 7× in this paper · explained in 3 episodes
• Clustering — 5× in this paper · explained in 2 episodes
• Credit assignment — 4× in this paper · explained in 3 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• International Conference on Learning Representations — 4× in this paper
• Embeddings — 3× in this paper · explained in 2 episodes
• GRPO — 3× in this paper · explained in 6 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Influence Functions — 2× in this paper · explained in 2 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Direct Preference Optimization (DPO) — 1× in this paper · explained in 9 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Sources

• Program Synthesis with Large Language Models
• Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
• Olmo 3
• Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Token-level Direct Preference Optimization

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