Less is More: Improving LLM Alignment via Preference Data Selection

• URL: http://arxiv.org/abs/2502.14560v3
• Date: Sat, 14 Jun 2025 13:50:43 GMT
• Title: Less is More: Improving LLM Alignment via Preference Data Selection
• Authors: Xun Deng, Han Zhong, Rui Ai, Fuli Feng, Zheng Wang, Xiangnan He,
• Abstract summary: 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.
• Score: 46.9163802899686
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Direct Preference Optimization (DPO) has emerged as a promising approach for aligning large language models with human preferences. While prior work mainly extends DPO from the aspect of the objective function, we instead improve DPO from the largely overlooked but critical aspect of data selection. Specifically, we address the issue of parameter shrinkage caused by noisy data by proposing a novel margin-maximization principle for dataset curation in DPO training. To further mitigate the noise in different reward models, we propose a Bayesian Aggregation approach that unifies multiple margin sources (external and implicit) into a single preference probability. Extensive experiments in diverse settings demonstrate the consistently high data efficiency of our approach. Remarkably, by using just 10\% of the Ultrafeedback dataset, our approach achieves 3\% to 8\% improvements across various Llama, Mistral, and Qwen models on the AlpacaEval2 benchmark. Furthermore, our approach seamlessly extends to iterative DPO, yielding a roughly 3\% improvement with 25\% online data, revealing the high redundancy in this presumed high-quality data construction manner. These results highlight the potential of data selection strategies for advancing preference optimization.

Related papers

• 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)
• Adaptive Sample Scheduling for Direct Preference Optimization [37.75208455935495]
  We introduce a novel problem: Sample Scheduling for DPO.<n>It aims to dynamically and adaptively schedule training samples based on the model's evolving states.<n>We propose SamS, an efficient and effective algorithm that adaptively selects samples in each training batch.
  arXiv  Detail & Related papers  (2025-06-08T10:26:09Z)
• Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences [13.588231827053923]
  Direct Preference Optimization (DPO) aligns text-to-image (T2I) generation models with human preferences using pairwise preference data.<n>We propose SmPO-Diffusion, a novel method for modeling preference distributions to improve the DPO objective.<n>Our approach effectively mitigates issues of excessive optimization and objective misalignment present in existing methods.
  arXiv  Detail & Related papers  (2025-06-03T09:47:22Z)
• ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment [94.36403843133616]
  Using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks.<n>Existing methods either lack a strong theoretical foundation or depend on restrictive reward function assumptions.<n>We propose an algorithm, ActiveDPO, that uses a theoretically grounded data selection criterion for non-linear reward functions.
  arXiv  Detail & Related papers  (2025-05-25T17:42:52Z)
• Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data [51.62162460809116]
  We introduce Dynamic Noise Preference Optimization (DNPO) to ensure consistent improvements across iterations.<n>In experiments with Zephyr-7B, DNPO consistently outperforms existing methods, showing an average performance boost of 2.6%.<n> DNPO shows a significant improvement in model-generated data quality, with a 29.4% win-loss rate gap compared to the baseline in GPT-4 evaluations.
  arXiv  Detail & Related papers  (2025-02-08T01:20:09Z)
• Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment [19.02679077706812]
  We study the problem of aligning large language models with human preference data. We propose direct preference optimization (Cal-DPO), a simple yet effective algorithm. The results of our experiments on a variety of standard benchmarks show that Cal-DPO remarkably improves off-the-shelf methods.
  arXiv  Detail & Related papers  (2024-12-19T04:31:56Z)
• Uncertainty-Penalized Direct Preference Optimization [52.387088396044206]
  We develop a pessimistic framework for DPO by introducing preference uncertainty penalization schemes. The penalization serves as a correction to the loss which attenuates the loss gradient for uncertain samples. We show improved overall performance compared to vanilla DPO, as well as better completions on prompts from high-uncertainty chosen/rejected responses.
  arXiv  Detail & Related papers  (2024-10-26T14:24:37Z)
• Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective [4.548047308860141]
  This study investigates the impact of different type of preference data on model performance. It aims to reduce their dependency on extensive amounts of preference data, which is expensive to collect.
  arXiv  Detail & Related papers  (2024-10-22T00:11:41Z)
• Reward-Augmented Data Enhances Direct Preference Alignment of LLMs [63.32585910975191]
  We introduce reward-conditioned Large Language Models (LLMs) that learn from the entire spectrum of response quality within the dataset.<n>We propose an effective yet simple data relabeling method that conditions the preference pairs on quality scores to construct a reward-augmented dataset.
  arXiv  Detail & Related papers  (2024-10-10T16:01:51Z)
• TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights [73.9088920210495]
  We propose a token-level importance sampling DPO objective named TIS-DPO that assigns importance weights to each token based on its reward. TIS-DPO significantly outperforms various baseline methods on harmlessness and helpfulness alignment and summarization tasks.
  arXiv  Detail & Related papers  (2024-10-06T04:03:00Z)
• 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)
• WPO: Enhancing RLHF with Weighted Preference Optimization [40.07940023654452]
  Reinforcement learning from human feedback (RLHF) is a promising solution to align large language models (LLMs) more closely with human values. Off-policy preference optimization often suffers from a distributional gap between the policy used for data collection and the target policy, leading to suboptimal optimization. We propose a novel strategy to mitigate this problem by simulating on-policy learning with off-policy preference data.
  arXiv  Detail & Related papers  (2024-06-17T17:59:13Z)
• Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models with human preferences. Our key idea is leveraging the human prior knowledge within the small (seed) data. We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• 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)
• Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization [34.29965046863887]
  Triple Preference Optimization (TPO) is a new preference learning method designed to enhance both reasoning and instruction-following abilities.<n>TPO achieves significant improvements over existing methods without substantially increasing response length across different dataset sizes.
  arXiv  Detail & Related papers  (2024-05-26T20:18:11Z)
• Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive [15.066029556877721]
  We show theoretically that the standard DPO loss can lead to a reduction of the model's likelihood of the preferred examples. We design DPO-Positive (DPOP), a new loss function and training procedure which avoids this failure mode. Surprisingly, we find that DPOP outperforms DPO and other fine-tuning procedures across a wide variety of datasets and downstream tasks.
  arXiv  Detail & Related papers  (2024-02-20T18:42:34Z)

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.