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.
arXiv:2609.06893v1 Announce Type: cross Abstract: Direct preference optimization DPO is a promising offline approach for aligning large language models (LLMs) due to its simplicity, computational eff...
arXiv:2504. 06659v2 Announce Type: replace-cross Abstract: Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like reinforcement learning with human feedback face notable challenges.
arXiv:2605. 12288v3 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even though generation is driven by per-token decisions.
The paper introduces DSPA, a dynamic sparse autoencoder (SAE) steering technique that aligns language model outputs with user preferences during inference, avoiding costly weight updates. DSPA constructs a conditional-difference map from preference triples to adjust token-active latents, improving MT‑Bench scores and matching AlpacaEval performance on models like Gemma‑2 and Qwen3 while preserving accuracy. It demonstrates robustness with limited preference data, outperforms the two‑stage RAHF‑SCIT pipeline in FLOPs, and reveals that preference directions are largely driven by discourse and stylistic cues.
arXiv:2512. 15765v3 Announce Type: replace Abstract: Data valuation is a natural framework for understanding which preference datasets matter most when aligning a Large Language Model (LLM) using multiple sources.
arXiv:2509. 23982v2 Announce Type: replace-cross Abstract: Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences.
The paper introduces GAP-DPO, a method for personalizing large language models by selecting preference pairs based on gradient alignment with user utility. It formalizes personalized preference learning as a geometry‑aligned optimization problem, showing that off‑policy sampling can shift DPO updates from error correction to reinforcement when preference margins align with utility gradients. Experiments demonstrate that GAP‑DPO improves stylistic fidelity, preference alignment, and overall generation quality over standard DPO variants.
The paper introduces BALIGN, a balanced data selection strategy designed to reduce catastrophic forgetting—referred to as the alignment tax—in large language models during preference-based alignment. By analyzing preference optimization gradients, the authors identify three data-centric features that influence parameter drift: the reference model's log-probability margin, token length differences between chosen and rejected responses, and TF‑IDF similarity to general capability corpora. BALIGN aggregates these features into a composite risk score to filter out high-risk preference samples, thereby preserving foundational capabilities while maintaining alignment gains with minimal computational overhead.
The paper reproduces five factuality alignment methods for large language models—three on‑policy RL approaches (PPO, GRPO, Dr.GRPO) and two offline preference optimization methods (DPO, KTO)—using a common benchmark and evaluation metrics. None of the methods consistently outperforms the base model, and the rewards appear to favor format, length, or brevity rather than factuality or relevance. The study also highlights problems with current evaluation practices, noting that metrics and benchmarks often fail to measure prompt relevance and rely on fragile LLM judges and retrieval for verification.
arXiv:2505. 10892v2 Announce Type: replace Abstract: Post-training LLMs with RLHF and preference optimization methods (e.
The paper introduces Geometric Anchor Preference Optimization (GAPO), a method that replaces the static reference policy in Direct Preference Optimization with a dynamic, geometry-aware anchor—a small adversarial perturbation of the current policy. GAPO uses this anchor to adaptively reweight preference pairs based on local sensitivity, and defines an Anchor Gap that approximates worst‑case local margin degradation. Experiments show that GAPO improves robustness to noisy supervision while matching or surpassing existing LLM alignment and reasoning benchmarks.
Aligning large language models to human preferences is crucial for real-world deployment but frequently incurs an alignment tax, leading to the catastrophic forgetting of pre-trained general capabilit...