Data-Centric Human Preference with Rationales for Direct Preference Alignment

• URL: http://arxiv.org/abs/2407.14477v4
• Date: Sun, 13 Jul 2025 19:41:48 GMT
• Title: Data-Centric Human Preference with Rationales for Direct Preference Alignment
• Authors: Hoang Anh Just, Ming Jin, Anit Sahu, Huy Phan, Ruoxi Jia,
• Abstract summary: We propose augmenting standard preference pairs with rationales that explain the reasoning behind the human preference.<n>Our comprehensive analysis demonstrates that incorporating rationales improves learning efficiency.<n>Our findings showcase the potential of thoughtful data design in preference learning.
• Score: 23.243583332894737
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aligning language models with human preferences through reinforcement learning from human feedback is crucial for their safe and effective deployment. The human preference is typically represented through comparison where one response is chosen over another for a given prompt. However, standard preference datasets often lack explicit information on why a particular choice was made, presenting an ambiguity that can hinder efficient learning and robust alignment, especially given the high cost of acquiring extensive human annotations. While many studies focus on algorithmic improvements, this work adopts a data-centric perspective, exploring how to enhance learning from existing preference data. We propose augmenting standard preference pairs with rationales that explain the reasoning behind the human preference. Specifically, we introduce a simple and principled framework that leverages machine-generated rationales to enrich preference data for preference optimization algorithms. Our comprehensive analysis demonstrates that incorporating rationales improves learning efficiency. Extensive experiments reveal some advantages: rationale-augmented learning accelerates convergence and can achieve higher final model performance. Furthermore, this approach is versatile and compatible with various direct preference optimization algorithms. Our findings showcase the potential of thoughtful data design in preference learning, demonstrating that enriching existing datasets with explanatory rationales can help unlock improvements in model alignment and annotation efficiency.

Related papers

• Intuitionistic Fuzzy Sets for Large Language Model Data Annotation: A Novel Approach to Side-by-Side Preference Labeling [0.0]
  This paper introduces a novel framework based on intuitionistic fuzzy sets (IFS) for modeling and aggregating human preferences in large language models (LLMs)<n>Our approach captures not only the degree of preference but also the uncertainty and hesitation inherent in human judgment through membership, non-membership, and hesitation degrees.<n> Experimental validation on multiple datasets demonstrates that our IFS-based approach significantly improves annotation consistency, reduces annotator fatigue, and produces higher-quality preference data.
  arXiv  Detail & Related papers  (2025-05-30T04:20:00Z)
• 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)
• Active Learning for Direct Preference Optimization [59.84525302418018]
  Direct preference optimization (DPO) is a form of reinforcement learning from human feedback.<n>We propose an active learning framework for DPO, which can be applied to collect human feedback online or to choose the most informative subset of already collected feedback offline.
  arXiv  Detail & Related papers  (2025-03-03T00:36:31Z)
• Preference learning made easy: Everything should be understood through win rate [25.849945888898997]
  This work presents a framework to understand preference learning starting from the sampling of pairwise preference data. First, we prove that the only evaluation of a generative model that respects both preferences and prevalences in the data distribution is a form of win rate. We then analyze preference learning methods as win rate optimization (WRO) or non-WRO.
  arXiv  Detail & Related papers  (2025-02-14T19:01:34Z)
• 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)
• LRHP: Learning Representations for Human Preferences via Preference Pairs [45.056558199304554]
  We introduce a preference representation learning task that aims to construct a richer and more structured representation of human preferences. We verify the utility of preference representations in two downstream tasks: preference data selection and preference margin prediction.
  arXiv  Detail & Related papers  (2024-10-06T14:48:28Z)
• Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
  We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-26T12:37:26Z)
• Leveraging Variation Theory in Counterfactual Data Augmentation for Optimized Active Learning [19.962212551963383]
  Active Learning (AL) allows models to learn interactively from user feedback. This paper introduces a counterfactual data augmentation approach to AL.
  arXiv  Detail & Related papers  (2024-08-07T14:55:04Z)
• Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring [16.38771834692938]
  We propose a novel framework capable of generating more faithful rationales and, more importantly, matching performance with black-box scoring systems. We first mimic the human assessment process by querying Large Language Models (LLMs) to generate a thought tree. We then summarise intermediate assessment decisions from each thought tree path for creating synthetic rationale data and rationale preference data.
  arXiv  Detail & Related papers  (2024-06-28T14:33:05Z)
• Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback [110.16220825629749]
  Learning from preference feedback has emerged as an essential step for improving the generation quality and performance of modern language models. In this work, we identify four core aspects of preference-based learning: preference data, learning algorithm, reward model, and policy training prompts. Our findings indicate that all aspects are important for performance, with better preference data leading to the largest improvements.
  arXiv  Detail & Related papers  (2024-06-13T16:17:21Z)
• Aligning Large Language Models with Self-generated Preference Data [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models (LLMs) 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)
• Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input [17.131441665935128]
  We study how to extract fine-grained data regarding why an example is preferred that is useful for learning more accurate reward models. Our findings suggest that incorporating pragmatic feature preferences is a promising approach for more efficient user-aligned reward learning.
  arXiv  Detail & Related papers  (2024-05-23T16:36:16Z)
• 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)
• ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference [16.73260713938154]
  A typical alignment procedure consists of supervised fine-tuning and preference learning. We introduce Point-wise Direct Preference Optimization, a novel preference learning method designed to harness point-wise feedback effectively. Our work also uncovers a novel connection between supervised fine-tuning and point-wise preference learning, culminating in Unified Language Model Alignment.
  arXiv  Detail & Related papers  (2023-12-05T07:52:12Z)
• Sample Efficient Preference Alignment in LLMs via Active Exploration [63.84454768573154]
  We take advantage of the fact that one can often choose contexts at which to obtain human feedback to most efficiently identify a good policy. We propose an active exploration algorithm to efficiently select the data and provide theoretical proof that it has a worst-case regret bound. Our method outperforms the baselines with limited samples of human preferences on several language models and four real-world datasets.
  arXiv  Detail & Related papers  (2023-12-01T00:54:02Z)
• A Data Driven Sequential Learning Framework to Accelerate and Optimize Multi-Objective Manufacturing Decisions [1.5771347525430772]
  This paper presents a novel data-driven Bayesian optimization framework that utilizes sequential learning to efficiently optimize complex systems. The proposed framework is particularly beneficial in practical applications where acquiring data can be expensive and resource intensive. It implies that the proposed data-driven framework can lead to similar manufacturing decisions with reduced costs and time.
  arXiv  Detail & Related papers  (2023-04-18T20:33:08Z)
• HyperImpute: Generalized Iterative Imputation with Automatic Model Selection [77.86861638371926]
  We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models. We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
  arXiv  Detail & Related papers  (2022-06-15T19:10:35Z)
• Compactness Score: A Fast Filter Method for Unsupervised Feature Selection [66.84571085643928]
  We propose a fast unsupervised feature selection method, named as, Compactness Score (CSUFS) to select desired features. Our proposed algorithm seems to be more accurate and efficient compared with existing algorithms.
  arXiv  Detail & Related papers  (2022-01-31T13:01:37Z)
• Training With Data Dependent Dynamic Learning Rates [8.833548357664608]
  We propose an optimization framework which accounts for difference in loss function characteristics across instances. Our framework learns a dynamic learning rate for each instance present in the dataset. We show that our framework can be used for personalization of a machine learning model towards a known targeted data distribution.
  arXiv  Detail & Related papers  (2021-05-27T21:52:29Z)

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.