HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs

• URL: http://arxiv.org/abs/2604.20140v1
• Date: Wed, 22 Apr 2026 03:08:30 GMT
• Title: HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs
• Abstract summary: We propose HiPO, an extension of DPO that separates responses into segments and computes loss as a weighted sum of the DPO loss for each segment.<n>Our approach enables segment-specific training while maintaining DPO's computational efficiency and training stability.<n>We demonstrate that for multiple 7B LLMs fine-tuned using HiPO and DPO on the Math Stack Exchange preference dataset, the models trained with HiPO outperform the others on a variety of common math benchmarks.
• Score: 2.497936211748472
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over dispreferred responses in their entirety and lacks the granularity to provide feedback on subsections of many-step solutions typical of reasoning tasks. Existing methods excel at either stable preference learning (e.g., DPO variants like KTO and RSO) or structured reasoning (e.g., ReMA's multi-agent RL framework, Tree of Thoughts), but fail to merge these complementary strengths. We propose HiPO (Hierarchical Preference Optimization), an extension of DPO that separates responses into reasoning segments (query clarification and context, reasoning steps, and answer) and computes loss as a weighted sum of the DPO loss for each segment. Our approach enables segment-specific training while maintaining DPO's computational efficiency and training stability. We demonstrate that for multiple 7B LLMs fine-tuned using HiPO and DPO on the Math Stack Exchange preference dataset, the models trained with HiPO outperform the others on a variety of common math benchmarks and achieve greater organization, logical flow, and consistency as measured by GPT-4.1.

Related papers

• Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems [72.27018654934386]
  Direct preference optimization (DPO) is a simple and effective alignment strategy for large language models (LLMs) based on pairwise preferences.<n>In recommender systems, however, user feedback is rarely pairwise.<n>We propose Mult-DPO, a tractable multinomial surrogate likelihood over set-wise preference events for the user-preference alignment of LLM-based recommender systems.
  arXiv  Detail & Related papers  (2026-06-08T18:53:45Z)
• Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization [60.87651283510059]
  Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs.<n>We propose Dynamic Pruning Policy Optimization (DPPO), a framework that enables dynamic pruning while preserving unbiased gradient estimation.<n>To mitigate the data sparsity induced by pruning, we introduce Dense Prompt Packing, a window-based greedy strategy.
  arXiv  Detail & Related papers  (2026-03-04T14:48:53Z)
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization [133.27496265096445]
  We show how to apply Group Relative Policy Optimization under multi-reward setting without examining its suitability.<n>We then introduce Group reward-Decoupled Normalization Policy Optimization (GDPO), a new policy optimization method to resolve these issues.<n>GDPO consistently outperforms GRPO, demonstrating its effectiveness and generalizability for multi-reward reinforcement learning optimization.
  arXiv  Detail & Related papers  (2026-01-08T18:59:24Z)
• HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMs [54.16300997612526]
  Large Language Models (LLMs) increasingly rely on Chain-of-Thought (CoT) reasoning to improve accuracy on complex tasks.<n>This paper introduces the Hybrid Policy Optimization (i.e., HiPO), a framework for adaptive reasoning control.<n> Experiments across mathematics and coding benchmarks demonstrate that HiPO can substantially reduce token length while maintaining or improving accuracy.
  arXiv  Detail & Related papers  (2025-09-28T16:46:12Z)
• ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning [14.034412856423529]
  Direct Preference Optimization (DPO) has gained attention for its simplicity and computational efficiency in aligning large language models (LLMs)<n>Recent advancements have extended DPO to multimodal scenarios, achieving strong performance.<n>Traditional DPO relies on binary preference optimization, rewarding or penalizing entire responses without considering fine-grained segment correctness.<n>We propose Adaptive Sentence-level Preference Optimization (ASPO), which evaluates individual sentences for more precise preference optimization.
  arXiv  Detail & Related papers  (2025-05-25T11:33:08Z)
• A Survey of Direct Preference Optimization [103.59317151002693]
  Large Language Models (LLMs) have demonstrated unprecedented generative capabilities.<n>Their alignment with human values remains critical for ensuring helpful and harmless deployments.<n>Direct Preference Optimization (DPO) has recently gained prominence as a streamlined alternative.
  arXiv  Detail & Related papers  (2025-03-12T08:45:15Z)
• MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples [22.521746860874305]
  This study introduces the MPPO algorithm, which leverages the average likelihood of model responses to fit the reward function.<n>Through a comparison of Point-wise, Pair-wise, and List-wise implementations, we found that the Pair-wise approach achieves the best performance.<n> Experimental results demonstrate MPPO's outstanding performance across various benchmarks.
  arXiv  Detail & Related papers  (2024-12-13T14:18:58Z)
• AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization [45.46582930202524]
  $alpha$-DPO is an adaptive preference optimization algorithm for large language models.<n>It balances the policy model and the reference model to achieve personalized reward margins.<n>It consistently outperforms DPO and SimPO across various model settings.
  arXiv  Detail & Related papers  (2024-10-14T04:29:57Z)
• TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees [19.99934360969673]
  We introduce Tree Preference Optimization (TPO), that does not sample paired preference responses from the preference tree.<n>TPO formulates the language model alignment as a Preference List Ranking problem.<n>The experimental results indicate that TPO consistently outperforms DPO across five public large language models on four datasets.
  arXiv  Detail & Related papers  (2024-10-10T22:22:05Z)
• Minor DPO reject penalty to increase training robustness [8.971332948872185]
  Learning from human preference is a paradigm used in large-scale language model (LLM) fine-tuning step to better align pretrained LLM to human preference for downstream task. Recently, Direct Preference Optimization (DPO) has been proposed to solve the alignment problem with a simplified RL-free method. In this article, we analyze the working mechanism of $beta$ in DPO, disclose its syntax difference between RL algorithm and DPO, and understand the potential shortage brought by the DPO simplification.
  arXiv  Detail & Related papers  (2024-08-19T09:29:31Z)
• Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization [75.1240295759264]
  We propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC.<n>We increase the consistency and informativeness of the pairwise preference signals through targeted modifications.<n>We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
  arXiv  Detail & Related papers  (2024-08-14T11:29:47Z)

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.