Preference-aware Influence-function-based Data Selection Method for Efficient Fine-Tuning

• URL: http://arxiv.org/abs/2605.21422v1
• Date: Wed, 20 May 2026 17:15:43 GMT
• Title: Preference-aware Influence-function-based Data Selection Method for Efficient Fine-Tuning
• Abstract summary: Existing methods usually represent the target behavior with a set of target examples, but often treat these examples as equally important.<n>We propose PRISM, which uses the current model's preference to weight target examples and construct a preference-aware target representation.<n> PRISM scores candidate training samples by their alignment with this representation, concentrating the data budget on samples more likely to move the model toward the target behavior.
• Score: 32.8917548788909
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As LLMs continue to scale, improving training efficiency increasingly depends on using data more effectively. Data selection addresses this problem by allocating a limited training budget to samples that best promote a target behavior. Existing methods usually represent the target behavior with a set of target examples, but often treat these examples as equally important. This can be inefficient because target examples may differ in their relevance to the current model: examples closer to the model's current behavior provide more actionable guidance than those farther away. We propose PRISM (PReference-aware Influence-function-based Data Selection Method for Efficient Fine-Tuning), which uses the current model's preference to weight target examples and construct a preference-aware target representation. PRISM then scores candidate training samples by their alignment with this representation, concentrating the data budget on samples more likely to move the model toward the target behavior. Theoretical analysis shows that this preference weighting yields a more effective first-order direction for increasing target-behavior preference. Experiments across model families and scales show that PRISM improves both efficient fine-tuning and safety-oriented SFT repair, demonstrating that precise target-behavior characterization is key to budget-efficient data selection.

Related papers

• Towards Understanding Valuable Preference Data for Large Language Model Alignment [85.38864561060088]
  Large language model (LLM) alignment is typically achieved through learning from human preference comparisons.<n>We assess data quality through individual influence on validation data using our newly proposed truncated influence function (TIF)<n>To this end, we combine them to offset their diverse error sources, resulting in a simple yet effective data selection rule.
  arXiv  Detail & Related papers  (2025-10-15T06:57:55Z)
• Adaptive Preference Optimization with Uncertainty-aware Utility Anchor [33.74005997646761]
  offline preference optimization methods are efficient for large language models (LLMs) alignment.<n>We propose a general framework for offline preference optimization methods, which introduces an anchoring function to estimate the uncertainties brought from preference data annotation.<n>Our method enables training even in scenarios where the data is unpaired, significantly enhancing data utilization efficiency.
  arXiv  Detail & Related papers  (2025-09-03T10:20:08Z)
• GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO [3.189559302776161]
  The ability to train high-performing reward models with few-shot data is critical for enhancing the efficiency and scalability of Reinforcement Learning from Human Feedback.<n>We propose a data augmentation and expansion framework that enables generative reward models trained on small datasets to achieve comparable performance to those trained on large-scale datasets.
  arXiv  Detail & Related papers  (2025-06-10T16:37:13Z)
• Efficient Data Selection at Scale via Influence Distillation [53.03573620682107]
  This paper introduces Influence Distillation, a mathematicallyjustified framework for data selection.<n>By distilling each sample's influence on a target distribution, our method assigns model-specific weights that are used to select training data.<n>Experiments show that Influence Distillation matches or outperforms state-of-the-art performance while achieving up to $3.5times$ faster selection.
  arXiv  Detail & Related papers  (2025-05-25T09:08:00Z)
• Enhancing Training Data Attribution with Representational Optimization [57.61977909113113]
  Training data attribution methods aim to measure how training data impacts a model's predictions.<n>We propose AirRep, a representation-based approach that closes this gap by learning task-specific and model-aligned representations explicitly for TDA.<n>AirRep introduces two key innovations: a trainable encoder tuned for attribution quality, and an attention-based pooling mechanism that enables accurate estimation of group-wise influence.
  arXiv  Detail & Related papers  (2025-05-24T05:17:53Z)
• 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)
• Behavior-Contextualized Item Preference Modeling for Multi-Behavior Recommendation [30.715182718492244]
  This paper introduces a novel approach, Behavior-Contextualized Item Preference Modeling (BCIPM) for multi-behavior recommendation. Our proposed Behavior-Contextualized Item Preference Network discerns and learns users' specific item preferences within each behavior. It then considers only those preferences relevant to the target behavior for final recommendations, significantly reducing noise from auxiliary behaviors.
  arXiv  Detail & Related papers  (2024-04-28T12:46:36Z)
• 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)
• Prediction-Oriented Bayesian Active Learning [51.426960808684655]
  Expected predictive information gain (EPIG) is an acquisition function that measures information gain in the space of predictions rather than parameters. EPIG leads to stronger predictive performance compared with BALD across a range of datasets and models.
  arXiv  Detail & Related papers  (2023-04-17T10:59:57Z)
• Improved Fine-tuning by Leveraging Pre-training Data: Theory and Practice [52.11183787786718]
  Fine-tuning a pre-trained model on the target data is widely used in many deep learning applications. Recent studies have empirically shown that training from scratch has the final performance that is no worse than this pre-training strategy. We propose a novel selection strategy to select a subset from pre-training data to help improve the generalization on the target task.
  arXiv  Detail & Related papers  (2021-11-24T06:18:32Z)

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.