arXiv:2606. 19744v1 Announce Type: cross Abstract: Aligning language models with human preferences often requires optimising multiple behavioural objectives.
arXiv:2602. 09533v2 Announce Type: replace Abstract: Direct preference optimization (DPO) has emerged as a promising approach for aligning large language models (LLMs) with human preferences.
arXiv:2410. 15595v4 Announce Type: replace Abstract: With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical.
GroupDPO introduces a memory‑efficient approach to group‑wise direct preference optimization for aligning large language models. By using first‑order linearization with per‑response coefficients, the method decouples samples during backpropagation, dramatically reducing peak memory usage and enabling scalable training with larger groups. Experiments in both offline and online settings show that leveraging multiple responses consistently outperforms single‑pair training, and adding a negative log‑likelihood term on positive responses is essential for performance gains and training stability.
The paper investigates how the quality of instructions used to generate response pairs affects preference learning for language models. It shows that low‑quality or ambiguous instructions limit the range of response quality, weakening preference signals, and introduces an instruction‑refinement pipeline that improves data quality without discarding examples. Experiments across models and benchmarks demonstrate that refining instructions leads to better alignment and complements other data‑improvement methods.
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.
arXiv:2502.14643v3 Announce Type: replace Abstract: Direct Preference Optimization (DPO) is a widely adopted offline algorithm for preference-based reinforcement learning from human feedback (RLHF),...
arXiv:2510. 05342v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models.
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:2510. 26707v2 Announce Type: replace-cross Abstract: As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw on their general knowledge but also to align with certain human value systems.
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 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.
arXiv:2509. 03647v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models.