Beyond Single: A Data Selection Principle for LLM Alignment via Fine-Grained Preference Signals

• URL: http://arxiv.org/abs/2508.07638v1
• Date: Mon, 11 Aug 2025 05:43:02 GMT
• Title: Beyond Single: A Data Selection Principle for LLM Alignment via Fine-Grained Preference Signals
• Authors: Jia Zhang, Yao Liu, Chen-Xi Zhang, Yi Liu, Yi-Xuan Jin, Lan-Zhe Guo, Yu-Feng Li,
• Abstract summary: We propose a novel, theoretically-grounded data selection principle for large language models.<n>We prove the optimality of this strategy by analyzing the loss bounds of the Direct Preference Optimization objective.<n>Our strategy achieves over 10% relative improvement against both the standard holistic preference and a stronger oracle.
• Score: 46.58760908162995
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Aligning Large Language Models (LLMs) with diverse human values requires moving beyond a single holistic "better-than" preference criterion. While collecting fine-grained, aspect-specific preference data is more reliable and scalable, existing methods like Direct Preference Optimization (DPO) struggle with the severe noise and conflicts inherent in such aggregated datasets. In this paper, we tackle this challenge from a data-centric perspective. We first derive the Direct Multi-Preference Optimization (DMPO) objective, and uncover a key Preference Divergence (PD) term that quantifies inter-aspect preference conflicts. Instead of using this term for direct optimization, we leverage it to formulate a novel, theoretically-grounded data selection principle. Our principle advocates for selecting a subset of high-consensus data-identified by the most negative PD values-for efficient DPO training. We prove the optimality of this strategy by analyzing the loss bounds of the DMPO objective in the selection problem. To operationalize our approach, we introduce practical methods of PD term estimation and length bias mitigation, thereby proposing our PD selection method. Evaluation on the UltraFeedback dataset with three varying conflict levels shows that our simple yet effective strategy achieves over 10% relative improvement against both the standard holistic preference and a stronger oracle using aggregated preference signals, all while boosting training efficiency and obviating the need for intractable holistic preference annotating, unlocking the potential of robust LLM alignment via fine-grained preference signals.

Related papers

• How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics [65.67654005892469]
  We show that proper instance-dependent sampling can yield stronger ranking guarantees, while skewed on-policy sampling can induce excessive concentration under structured preferences.<n>We then analyze iterative alignment dynamics in which the learned policy feeds back into future sampling and reference policies.<n>Our theoretical insights extend to Direct Preference Optimization, indicating the phenomena we captured are common to a broader class of preference-alignment methods.
  arXiv  Detail & Related papers  (2026-02-12T17:11:08Z)
• Diversity First, Quality Later: A Two-Stage Assumption for Language Model Alignment [16.059172179404467]
  The alignment of language models (LMs) with human preferences is critical for building reliable AI systems.<n>Recently, Direct Preference Optimization (DPO) was proposed as a LM alignment method that directly optimize the policy from static preference data.<n>We show on-policy data is not always optimal, with systematic effectiveness difference emerging between static and on-policy preference candidates.
  arXiv  Detail & Related papers  (2025-08-14T11:05:18Z)
• Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap [13.89078939095465]
  We introduce a novel difficulty-based data selection strategy for preference datasets, grounded in the DPO implicit reward mechanism.<n>Our approach consistently outperforms five strong baselines across multiple datasets and alignment tasks.
  arXiv  Detail & Related papers  (2025-08-06T07:24:14Z)
• Less is More: Improving LLM Alignment via Preference Data Selection [46.9163802899686]
  Direct Preference Optimization (DPO) has emerged as a promising approach for aligning large language models with human preferences.<n>We propose a novel margin-maximization principle for dataset curation in DPO training.<n>We show that our approach seamlessly extends to iterative DPO, yielding a roughly 3% improvement with 25% online data.
  arXiv  Detail & Related papers  (2025-02-20T13:45:17Z)
• Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization [75.1240295759264]
  We propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC.<n>We increase the consistency and informativeness of the pairwise preference signals through targeted modifications.<n>We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
  arXiv  Detail & Related papers  (2024-08-14T11:29:47Z)
• Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
  Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values. We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO) Our method is versatile and can be readily adapted to various preference optimization frameworks.
  arXiv  Detail & Related papers  (2024-06-04T20:33:22Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• Towards Efficient Exact Optimization of Language Model Alignment [93.39181634597877]
  Direct preference optimization (DPO) was proposed to directly optimize the policy from preference data. We show that DPO derived based on the optimal solution of problem leads to a compromised mean-seeking approximation of the optimal solution in practice. We propose efficient exact optimization (EXO) of the alignment objective.
  arXiv  Detail & Related papers  (2024-02-01T18:51:54Z)
• Statistical Rejection Sampling Improves Preference Optimization [42.57245965632205]
  We introduce a novel approach to source preference data from the target optimal policy using rejection sampling. We also propose a unified framework that enhances the loss functions used in both Sequence Likelihood (SLiC) and Direct Preference Optimization (DPO) from a preference modeling standpoint.
  arXiv  Detail & Related papers  (2023-09-13T01:07:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.