DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data

• URL: http://arxiv.org/abs/2505.15074v2
• Date: Tue, 10 Jun 2025 03:41:45 GMT
• Title: DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data
• Authors: Yuhang Zhou, Jing Zhu, Shengyi Qian, Zhuokai Zhao, Xiyao Wang, Xiaoyu Liu, Ming Li, Paiheng Xu, Wei Ai, Furong Huang,
• Abstract summary: We propose a principled extension to GRPO that addresses inter-group imbalance with two key innovations.<n> Domain-aware reward scaling counteracts frequency bias by reweighting optimization based on domain prevalence.<n>Difficulty-aware reward scaling leverages prompt-level self-consistency to identify and prioritize uncertain prompts that offer greater learning value.
• Score: 29.06340707914799
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). Among RLHF methods, Group Relative Policy Optimization (GRPO) has gained attention for its simplicity and strong performance, notably eliminating the need for a learned value function. However, GRPO implicitly assumes a balanced domain distribution and uniform semantic alignment across groups - assumptions that rarely hold in real-world datasets. When applied to multi-domain, imbalanced data, GRPO disproportionately optimizes for dominant domains, neglecting underrepresented ones and resulting in poor generalization and fairness. We propose Domain-Informed Self-Consistency Policy Optimization (DISCO), a principled extension to GRPO that addresses inter-group imbalance with two key innovations. Domain-aware reward scaling counteracts frequency bias by reweighting optimization based on domain prevalence. Difficulty-aware reward scaling leverages prompt-level self-consistency to identify and prioritize uncertain prompts that offer greater learning value. Together, these strategies promote more equitable and effective policy learning across domains. Extensive experiments across multiple LLMs and skewed training distributions show that DISCO improves generalization, outperforms existing GRPO variants by 5% on Qwen3 models, and sets new state-of-the-art results on multi-domain alignment benchmarks.

Related papers

• Adversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimization [6.619253289031494]
  Single Domain Generalization aims to develop models capable of generalizing to unseen target domains using only one source domain.<n>We propose LEAwareSGD, a novel Lyapunov Exponent (LE)-guided optimization approach inspired by dynamical systems theory.<n>Experiments on PACS, OfficeHome, and DomainNet demonstrate that LEAwareSGD yields substantial generalization gains.
  arXiv  Detail & Related papers  (2025-07-06T09:03:08Z)
• Global Variational Inference Enhanced Robust Domain Adaptation [7.414646586981638]
  We propose a framework that learns continuous, class-conditional global priors via variational inference to enable structure-aware cross-domain alignment.<n>GVI-DA minimizes domain gaps through latent feature reconstruction, and mitigates posterior collapse using global codebook learning with randomized sampling.<n>It further improves robustness by discarding low-confidence pseudo-labels and generating reliable target-domain samples.
  arXiv  Detail & Related papers  (2025-07-04T04:43:23Z)
• On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization [52.76330545825083]
  Reinforcement learning (RL) has become popular in enhancing the reasoning capabilities of large language models (LLMs)<n>We identify a previously unrecognized phenomenon we term Lazy Likelihood Displacement (LLD), wherein the likelihood of correct responses marginally increases or even decreases during training.<n>We develop a method called NTHR, which downweights penalties on tokens contributing to the LLD. Unlike prior DPO-based approaches, NTHR takes advantage of GRPO's group-based structure, using correct responses as anchors to identify influential tokens.
  arXiv  Detail & Related papers  (2025-05-24T18:58:51Z)
• Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO [68.44918104224818]
  Autoregressive image generation presents unique challenges distinct from Chain-of-Thought (CoT) reasoning.<n>This study provides the first comprehensive investigation of the GRPO and DPO algorithms in autoregressive image generation.<n>Our findings reveal that GRPO and DPO exhibit distinct advantages, and crucially, that reward models possessing stronger intrinsic generalization capabilities potentially enhance the generalization potential of the applied RL algorithms.
  arXiv  Detail & Related papers  (2025-05-22T17:59:49Z)
• DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization [55.06360285372418]
  Group Relative Policy Optimization is a reinforcement learning method for large reasoning models (LRMs)<n>In this work, we analyze the GRPO objective under a binary reward setting and reveal an inherent limitation of question-level difficulty bias.<n>We introduce a new Discriminative Constrained Optimization framework for reinforcing LRMs, grounded in the principle of discriminative learning.
  arXiv  Detail & Related papers  (2025-05-18T11:08:32Z)
• Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler [45.71475375161575]
  In Open-Set Domain Generalization, the model is exposed to both new variations of data appearance (domains) and open-set conditions. We propose the Evidential Bi-Level Hardest Domain Scheduler (EBiL-HaDS) to achieve an adaptive domain scheduler.
  arXiv  Detail & Related papers  (2024-09-26T05:57:35Z)
• Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment [58.049113055986375]
  We develop a single stage approach named Alignment with Integrated Human Feedback (AIHF) to train reward models and the policy.<n>The proposed approach admits a suite of efficient algorithms, which can easily reduce to, and leverage, popular alignment algorithms.<n>We demonstrate the efficiency of the proposed solutions with extensive experiments involving alignment problems in LLMs and robotic control problems in MuJoCo.
  arXiv  Detail & Related papers  (2024-06-11T01:20:53Z)
• Group Robust Preference Optimization in Reward-free RLHF [23.622835830345725]
  We propose a novel Group Robust Preference Optimization (GRPO) method to align large language models to individual groups' preferences robustly. To achieve this, GRPO adaptively and sequentially weights the importance of different groups, prioritizing groups with worse cumulative loss. We significantly improved performance for the worst-performing groups, reduced loss imbalances across groups, and improved probability accuracies.
  arXiv  Detail & Related papers  (2024-05-30T17:50:04Z)
• Domain-Specific Risk Minimization for Out-of-Distribution Generalization [104.17683265084757]
  We first establish a generalization bound that explicitly considers the adaptivity gap. We propose effective gap estimation methods for guiding the selection of a better hypothesis for the target. The other method is minimizing the gap directly by adapting model parameters using online target samples.
  arXiv  Detail & Related papers  (2022-08-18T06:42:49Z)
• Self-balanced Learning For Domain Generalization [64.99791119112503]
  Domain generalization aims to learn a prediction model on multi-domain source data such that the model can generalize to a target domain with unknown statistics. Most existing approaches have been developed under the assumption that the source data is well-balanced in terms of both domain and class. We propose a self-balanced domain generalization framework that adaptively learns the weights of losses to alleviate the bias caused by different distributions of the multi-domain source data.
  arXiv  Detail & Related papers  (2021-08-31T03:17:54Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)

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.