ProDS: Preference-oriented Data Selection for Instruction Tuning

• URL: http://arxiv.org/abs/2505.12754v1
• Date: Mon, 19 May 2025 06:28:14 GMT
• Title: ProDS: Preference-oriented Data Selection for Instruction Tuning
• Authors: Wenya Guo, Zhengkun Zhang, Xumeng Liu, Ying Zhang, Ziyu Lu, Haoze Zhu, Xubo Liu, Ruxue Yan,
• Abstract summary: We propose Preference-oriented Data Selection method (ProDS) that scores training samples based on their alignment with preferences observed in the target set.<n>Our key innovation lies in shifting the data selection criteria from merely estimating features for accurate response generation to explicitly aligning training samples with human preferences in target tasks.
• Score: 16.416482636797504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Instruction data selection aims to identify a high-quality subset from the training set that matches or exceeds the performance of the full dataset on target tasks. Existing methods focus on the instruction-to-response mapping, but neglect the human preference for diverse responses. In this paper, we propose Preference-oriented Data Selection method (ProDS) that scores training samples based on their alignment with preferences observed in the target set. Our key innovation lies in shifting the data selection criteria from merely estimating features for accurate response generation to explicitly aligning training samples with human preferences in target tasks. Specifically, direct preference optimization (DPO) is employed to estimate human preferences across diverse responses. Besides, a bidirectional preference synthesis strategy is designed to score training samples according to both positive preferences and negative preferences. Extensive experimental results demonstrate our superiority to existing task-agnostic and targeted methods.

Related papers

• 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)
• Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF [67.48004037550064]
  We propose an active learning approach to efficiently select prompt and preference pairs.<n>Our method evaluates the gradients of all potential preference annotations to assess their impact on model updates.<n> Experimental results demonstrate that our method outperforms the baseline by up to 5% in win rates against the chosen completion.
  arXiv  Detail & Related papers  (2025-03-28T04:22:53Z)
• Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners [16.863492060519157]
  This work addresses the challenge of personalizing trajectories generated in automated decision-making systems.<n>We propose a resource-efficient approach that enables rapid adaptation to individual users' preferences.
  arXiv  Detail & Related papers  (2025-03-24T05:11:58Z)
• Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization [66.67988187816185]
  We aim to emphscale up the number of on-policy samples via repeated random sampling to improve alignment performance.<n>Our experiments reveal that this strategy leads to a emphdecline in performance as the sample size increases.<n>We introduce a scalable preference data construction strategy that consistently enhances model performance as the sample scale increases.
  arXiv  Detail & Related papers  (2025-02-24T04:22:57Z)
• A Systematic Examination of Preference Learning through the Lens of Instruction-Following [83.71180850955679]
  We use a novel synthetic data generation pipeline to generate 48,000 instruction unique-following prompts.<n>With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS)<n>Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements.<n>High-contrast preference pairs generally outperform low-contrast pairs; however, combining both often yields the best performance.
  arXiv  Detail & Related papers  (2024-12-18T15:38:39Z)
• ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning [29.001249598245]
  We introduce Reward-Oriented inStruction data sElection to optimize data selection for task-specific instruction tuning.<n> ROSE adapts an influence formulation to approximate the influence of training data points relative to a few-shot preference validation set to select the most task-related training data points.
  arXiv  Detail & Related papers  (2024-12-01T01:01:09Z)
• TSDS: Data Selection for Task-Specific Model Finetuning [39.19448080265558]
  The efficacy of task-specific finetuning largely depends on the selection of appropriate training data.<n>We present TSDS (Task-Specific Data Selection), a framework to select data for task-specific model finetuning.<n>We show that instruction tuning using data selected by our method with a 1% selection ratio often outperforms using the full dataset.
  arXiv  Detail & Related papers  (2024-10-15T05:54:17Z)
• 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 show that our approach consistently boosts DPO by a considerable margin.<n>Our method not only maximizes the utility of preference data but also mitigates the issue of unlearning, demonstrating its broad effectiveness beyond mere data expansion.
  arXiv  Detail & Related papers  (2024-10-10T16:01:51Z)
• Towards Comprehensive Preference Data Collection for Reward Modeling [15.495910034714187]
  Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models with human preferences. We propose a framework for preference data collection, decomposing the process into four incremental steps. This structured approach ensures the collection of high-quality preferences while reducing reliance on human labor.
  arXiv  Detail & Related papers  (2024-06-24T09:40:39Z)
• 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)
• LESS: Selecting Influential Data for Targeted Instruction Tuning [64.78894228923619]
  We propose LESS, an efficient algorithm to estimate data influences and perform Low-rank gradiEnt Similarity Search for instruction data selection. We show that training on a LESS-selected 5% of the data can often outperform training on the full dataset across diverse downstream tasks. Our method goes beyond surface form cues to identify data that the necessary reasoning skills for the intended downstream application.
  arXiv  Detail & Related papers  (2024-02-06T19:18:04Z)
• DsDm: Model-Aware Dataset Selection with Datamodels [81.01744199870043]
  Standard practice is to filter for examples that match human notions of data quality. We find that selecting according to similarity with "high quality" data sources may not increase (and can even hurt) performance compared to randomly selecting data. Our framework avoids handpicked notions of data quality, and instead models explicitly how the learning process uses train datapoints to predict on the target tasks.
  arXiv  Detail & Related papers  (2024-01-23T17:22:00Z)

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.