Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning

• URL: http://arxiv.org/abs/2406.17312v2
• Date: Fri, 11 Oct 2024 06:51:32 GMT
• Title: Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning
• Authors: Sen Yang, Leyang Cui, Deng Cai, Xinting Huang, Shuming Shi, Wai Lam,
• Abstract summary: Iterative preference learning requires online annotated preference labels. We study strategies to select worth-annotating response pairs for cost-efficient annotation.
• Score: 81.69044784288005
• License:
• Abstract: Iterative preference learning, though yielding superior performances, requires online annotated preference labels. In this work, we study strategies to select worth-annotating response pairs for cost-efficient annotation while achieving competitive or even better performances compared with the random selection baseline for iterative preference learning. Built on assumptions regarding uncertainty and distribution shifts, we propose a comparative view to rank the implicit reward margins as predicted by DPO to select the response pairs that yield more benefits. Through extensive experiments, we show that annotating those response pairs with small margins is generally better than large or random, under both single- and multi-iteration scenarios. Besides, our empirical results suggest allocating more annotation budgets in the earlier iterations rather than later across multiple iterations.

Related papers

• 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)
• Calibrated Multi-Preference Optimization for Aligning Diffusion Models [92.90660301195396]
  Calibrated Preference Optimization (CaPO) is a novel method to align text-to-image (T2I) diffusion models. CaPO incorporates the general preference from multiple reward models without human annotated data. Experimental results show that CaPO consistently outperforms prior methods.
  arXiv  Detail & Related papers  (2025-02-04T18:59:23Z)
• 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. With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS) Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements. 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)
• 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)
• 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)
• Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization [105.3612692153615]
  We propose a new axis based on eliciting preferences jointly over instruction-response pairs. Joint preferences over instruction and response pairs can significantly enhance the alignment of large language models.
  arXiv  Detail & Related papers  (2024-03-31T02:05:40Z)
• Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning [76.43827771613127]
  In this paper, we investigate task-specific preferences between pairs of input texts as a new alternative way for such auxiliary data annotation. We propose a novel multi-task learning framework, called prefer-to-classify (P2C), which can enjoy the cooperative effect of learning both the given classification task and the auxiliary preferences.
  arXiv  Detail & Related papers  (2023-06-08T04:04:47Z)
• Online Active Model Selection for Pre-trained Classifiers [72.84853880948894]
  We design an online selective sampling approach that actively selects informative examples to label and outputs the best model with high probability at any round. Our algorithm can be used for online prediction tasks for both adversarial and streams.
  arXiv  Detail & Related papers  (2020-10-19T19:53:15Z)

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.