DCRM: A Heuristic to Measure Response Pair Quality in Preference Optimization

• URL: http://arxiv.org/abs/2506.14157v1
• Date: Tue, 17 Jun 2025 03:37:41 GMT
• Title: DCRM: A Heuristic to Measure Response Pair Quality in Preference Optimization
• Authors: Chengyu Huang, Tanya Goyal,
• Abstract summary: We study 3 types of commonly used preference datasets, classified along two axes: the source of the responses and the preference labeling function.<n>We establish a general correlation between higher Distance Calibrated Reward Margin of the training set and better learning outcome.<n>Our method produces training datasets that can further improve models' performance on AlpacaEval, MT-Bench, and Arena-Hard.
• Score: 13.366219858094297
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent research has attempted to associate preference optimization (PO) performance with the underlying preference datasets. In this work, our observation is that the differences between the preferred response $y^+$ and dispreferred response $y^-$ influence what LLMs can learn, which may not match the desirable differences to learn. Therefore, we use distance and reward margin to quantify these differences, and combine them to get Distance Calibrated Reward Margin (DCRM), a metric that measures the quality of a response pair for PO. Intuitively, DCRM encourages minimal noisy differences and maximal desired differences. With this, we study 3 types of commonly used preference datasets, classified along two axes: the source of the responses and the preference labeling function. We establish a general correlation between higher DCRM of the training set and better learning outcome. Inspired by this, we propose a best-of-$N^2$ pairing method that selects response pairs with the highest DCRM. Empirically, in various settings, our method produces training datasets that can further improve models' performance on AlpacaEval, MT-Bench, and Arena-Hard over the existing training sets.

Related papers

• Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks [81.44256822500257]
  RLHF has emerged as a predominant approach for aligning artificial intelligence systems with human preferences.<n> RLHF exhibits insufficient compliance capabilities when confronted with complex multi-instruction tasks.<n>We propose a novel Multi-level Aware Preference Learning (MAPL) framework, capable of enhancing multi-instruction capabilities.
  arXiv  Detail & Related papers  (2025-05-19T08:33:11Z)
• Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment [35.80989342492335]
  noisy preferences in human feedback can lead to reward misgeneralization.<n>This paper aims to identify how noisy preferences differ from human-aligned preferences in reward modeling.<n>We propose an online Collaborative Reward Modeling framework to achieve robust preference learning.
  arXiv  Detail & Related papers  (2025-05-15T10:58:20Z)
• AMPO: Active Multi-Preference Optimization for Self-play Preference Selection [16.230186347702737]
  Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses.<n>We propose $textitActive Multi-Preference Optimization$ (AMPO), a novel approach that combines on-policy generation, a multi-preference group-contrastive loss, and active subset selection.<n>AMPO achieves state-of-the-art results on $textitAlpacaEval$ using Llama 8B and Mistral Mist 7B.
  arXiv  Detail & Related papers  (2025-02-25T15:29:51Z)
• 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)
• 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)
• 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)
• 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)
• Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning [55.96599486604344]
  We introduce an approach aimed at enhancing the reasoning capabilities of Large Language Models (LLMs) through an iterative preference learning process. We use Monte Carlo Tree Search (MCTS) to iteratively collect preference data, utilizing its look-ahead ability to break down instance-level rewards into more granular step-level signals. The proposed algorithm employs Direct Preference Optimization (DPO) to update the LLM policy using this newly generated step-level preference data.
  arXiv  Detail & Related papers  (2024-05-01T11:10:24Z)
• Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts [95.09994361995389]
  Relative Preference Optimization (RPO) is designed to discern between more and less preferred responses derived from both identical and related prompts. RPO has demonstrated a superior ability to align large language models with user preferences and to improve their adaptability during the training process.
  arXiv  Detail & Related papers  (2024-02-12T22:47:57Z)
• On Diversified Preferences of Large Language Model Alignment [51.26149027399505]
  This paper presents the first quantitative analysis of the experimental scaling law for reward models with varying sizes. Our analysis reveals that the impact of diversified human preferences depends on both model size and data size. Larger models with sufficient capacity mitigate the negative effects of diverse preferences, while smaller models struggle to accommodate them.
  arXiv  Detail & Related papers  (2023-12-12T16:17:15Z)

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.