TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization

• URL: http://arxiv.org/abs/2506.14574v1
• Date: Tue, 17 Jun 2025 14:30:06 GMT
• Title: TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization
• Authors: Mingkang Zhu, Xi Chen, Zhongdao Wang, Bei Yu, Hengshuang Zhao, Jiaya Jia,
• Abstract summary: Recent advancements in reinforcement learning have shown that utilizing fine-grained token-level reward models can substantially enhance the performance of Proximal Policy Optimization (PPO)<n>It is challenging to leverage such token-level reward as guidance for Direct Preference Optimization (DPO)<n>This work decomposes PPO into a sequence of token-level proximal policy optimization problems and then frames the problem of token-level PPO with token-level reward guidance.
• Score: 73.16975077770765
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in reinforcement learning from human feedback have shown that utilizing fine-grained token-level reward models can substantially enhance the performance of Proximal Policy Optimization (PPO) in aligning large language models. However, it is challenging to leverage such token-level reward as guidance for Direct Preference Optimization (DPO), since DPO is formulated as a sequence-level bandit problem. To address this challenge, this work decomposes the sequence-level PPO into a sequence of token-level proximal policy optimization problems and then frames the problem of token-level PPO with token-level reward guidance, from which closed-form optimal token-level policy and the corresponding token-level reward can be derived. Using the obtained reward and Bradley-Terry model, this work establishes a framework of computable loss functions with token-level reward guidance for DPO, and proposes a practical reward guidance based on the induced DPO reward. This formulation enables different tokens to exhibit varying degrees of deviation from reference policy based on their respective rewards. Experiment results demonstrate that our method achieves substantial performance improvements over DPO, with win rate gains of up to 7.5 points on MT-Bench, 6.2 points on AlpacaEval 2, and 4.3 points on Arena-Hard. Code is available at https://github.com/dvlab-research/TGDPO.

Related papers

• Learning Explainable Dense Reward Shapes via Bayesian Optimization [45.34810347865996]
  We frame reward shaping as an optimization problem focused on token-level credit assignment.<n>We use explainability methods such as SHAP and LIME to estimate per-token rewards from the reward model.<n>Our experiments show that achieving a better balance of token-level reward attribution leads to performance improvements over baselines.
  arXiv  Detail & Related papers  (2025-04-22T21:09:33Z)
• CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models [68.26281707780761]
  This paper introduces Completion Pruning Policy Optimization (CPPO) to accelerate the training of reasoning models.<n>We show that CPPO achieves up to $8.32times$ speedup on GSM8K and $3.51times$ on Math while preserving or even enhancing the accuracy compared to the original GRPO.
  arXiv  Detail & Related papers  (2025-03-28T11:30:05Z)
• AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation [46.72611855060883]
  We propose an RLHF-equivalent distillation method for token-level reward optimization.<n> Experimental results demonstrate the superiority of our AlignDistil over existing methods.
  arXiv  Detail & Related papers  (2025-03-04T17:57:09Z)
• Entropy Controllable Direct Preference Optimization [3.536605202672355]
  We propose a simple modification to DPO, H-DPO, which allows for control over the entropy of the resulting policy.<n>In our experiments, we show that H-DPO outperformed DPO across various tasks, demonstrating superior results in pass@$k$ evaluations for mathematical tasks.
  arXiv  Detail & Related papers  (2024-11-12T07:09:44Z)
• $α$-DPO: Adaptive Reward Margin is What Direct Preference Optimization Needs [45.46582930202524]
  $alpha$-DPO is an adaptive preference optimization algorithm for large language models. It balances the policy model and the reference model to achieve personalized reward margins. It consistently outperforms DPO and SimPO across various model settings.
  arXiv  Detail & Related papers  (2024-10-14T04:29:57Z)
• TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights [73.9088920210495]
  We propose a token-level importance sampling DPO objective named TIS-DPO that assigns importance weights to each token based on its reward.<n>TIS-DPO significantly outperforms various baseline methods on harmlessness and helpfulness alignment and summarization tasks.
  arXiv  Detail & Related papers  (2024-10-06T04:03:00Z)
• Understanding Reference Policies in Direct Preference Optimization [50.67309013764383]
  Direct Preference Optimization (DPO) has become a widely used training method for the instruction fine-tuning of large language models (LLMs) This work explores an under-investigated aspect of DPO - its dependency on the reference model or policy.
  arXiv  Detail & Related papers  (2024-07-18T17:08:10Z)
• DPO Meets PPO: Reinforced Token Optimization for RLHF [35.638723885233475]
  We introduce an algorithm that learns the token-wise reward function from preference data and performs policy optimization based on this learned token-wise reward signal.<n>Experiments demonstrate that textttRTO performs better than PPO and other direct preference learning algorithms.
  arXiv  Detail & Related papers  (2024-04-29T17:58:30Z)
• Provably Efficient Exploration in Policy Optimization [117.09887790160406]
  This paper proposes an Optimistic variant of the Proximal Policy Optimization algorithm (OPPO) OPPO achieves $tildeO(sqrtd2 H3 T )$ regret. To the best of our knowledge, OPPO is the first provably efficient policy optimization algorithm that explores.
  arXiv  Detail & Related papers  (2019-12-12T08:40:02Z)

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.