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

arXiv: https://arxiv.org/abs/2506.14574 · HTML: https://mlsanity.com/paper/2506.14574/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 17 Jun 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [UltraFeedback: Boosting Language Models with Scaled AI Feedback](https://mlsanity.com/paper/2310.01377/) (2023)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts](https://mlsanity.com/paper/2406.12845/) (2024)
- [From r to Q^*: Your Language Model is Secretly a Q-Function](https://mlsanity.com/paper/2404.12358/) (2024)
- [Fine-tuning Language Models for Factuality](https://mlsanity.com/paper/2311.08401/) (2023)
- [Disentangling Length from Quality in Direct Preference Optimization](https://mlsanity.com/paper/2403.19159/) (2024)
- [Offline RL for Natural Language Generation with Implicit Language Q Learning](https://mlsanity.com/paper/2206.11871/) (2022)
- [Token-level Direct Preference Optimization](https://mlsanity.com/paper/2404.11999/) (2024)
- [DPO Meets PPO: Reinforced Token Optimization for RLHF](https://mlsanity.com/paper/2404.18922/) (2024)
- [Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback](https://mlsanity.com/paper/2406.09279/) (2024)
- [On the Weaknesses of Reinforcement Learning for Neural Machine Translation](https://mlsanity.com/paper/1907.01752/) (2019)
- [A Dense Reward View on Aligning Text-to-Image Diffusion with Preference](https://mlsanity.com/paper/2402.08265/) (2024)
- [Preference-grounded Token-level Guidance for Language Model Fine-tuning](https://mlsanity.com/paper/2306.00398/) (2023)
- [Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data](https://mlsanity.com/paper/2408.14874/) (2024)
- [Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model](https://mlsanity.com/paper/2501.02790/) (2025)
- [Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective](https://mlsanity.com/paper/2502.14340/) (2025)
- [Aligning CodeLLMs with Direct Preference Optimization](https://mlsanity.com/paper/2410.18585/) (2024)

## Built on by (most cited first, 5 of 5)

- [Autoregressive Direct Preference Optimization](https://mlsanity.com/paper/2602.09533/) (2026)
- [Extreme Region Policy Distillation](https://mlsanity.com/paper/2605.25582/) (2026)
- [Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs](https://mlsanity.com/paper/2606.12590/) (2026)
- [KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment](https://mlsanity.com/paper/2607.03166/) (2026)
- [Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization](https://mlsanity.com/paper/2608.09568/) (2026)

## Abstract (arXiv)

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.