Preference Tuning LLMs with Direct Preference Optimization Methods

Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings

arXiv:2606. 19744v1 Announce Type: cross Abstract: Aligning language models with human preferences often requires optimising multiple behavioural objectives.

Boosting Direct Preference Optimization with Penalization

arXiv:2606. 12505v1 Announce Type: cross Abstract: Offline preference optimization has become a practical substitute for reinforcement learning from human feedback, but pairwise objectives such as Direct Preference Optimization (DPO) and its variants use only the chosen and rejected responses stored in a static dataset.

A Zeroth-Order Paradigm for LLM Preference Alignment

The paper introduces Comparison-based Preference Optimization (ComPO), a zeroth-order method that aligns large language models with human preferences using comparison oracles instead of direct differentiable loss optimization. It provides theoretical convergence guarantees for both offline and online variants under smoothness, gradient sparsity, and oracle compatibility assumptions, and establishes performance bounds under local coverage and in-distribution reward accuracy. Experiments on several LLMs (Mistral, Llama, Gemma-2, Qwen3, Gemma-3) show that ComPO outperforms existing direct alignment methods, achieving higher length-controlled win rates and diagnostics that suggest mitigation of likelihood displacement.

Optimizing your LLM in production

Direct Preference Optimization Beyond Chatbots

Make LLM Fine-tuning 2x faster with Unsloth and 🤗 TRL