Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization

• URL: http://arxiv.org/abs/2410.05255v2
• Date: Tue, 01 Jul 2025 16:20:45 GMT
• Title: Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization
• Authors: Daoan Zhang, Guangchen Lan, Dong-Jun Han, Wenlin Yao, Xiaoman Pan, Hongming Zhang, Mingxiao Li, Pengcheng Chen, Yu Dong, Christopher Brinton, Jiebo Luo,
• Abstract summary: Self-Sampling Preference Optimization (SSPO) is a new alignment method for post-training reinforcement learning.<n>SSPO eliminates the need for paired data and reward models while retaining the training stability of SFT.<n>SSPO surpasses all previous approaches on the text-to-image benchmarks and demonstrates outstanding performance on the text-to-video benchmarks.
• Score: 67.8738082040299
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement learning (RL) methods; the former is stable during training but suffers from limited generalization, while the latter, despite its stronger generalization capability, relies on additional preference data or reward models and carries the risk of reward exploitation. In order to preserve the advantages of both SFT and RL -- namely, eliminating the need for paired data and reward models while retaining the training stability of SFT and the generalization ability of RL -- a new alignment method, Self-Sampling Preference Optimization (SSPO), is proposed in this paper. SSPO introduces a Random Checkpoint Replay (RCR) strategy that utilizes historical checkpoints to construct paired data, thereby effectively mitigating overfitting. Simultaneously, a Self-Sampling Regularization (SSR) strategy is employed to dynamically evaluate the quality of generated samples; when the generated samples are more likely to be winning samples, the approach automatically switches from DPO (Direct Preference Optimization) to SFT, ensuring that the training process accurately reflects the quality of the samples. Experimental results demonstrate that SSPO not only outperforms existing methods on text-to-image benchmarks, but its effectiveness has also been validated in text-to-video tasks. We validate SSPO across both text-to-image and text-to-video benchmarks. SSPO surpasses all previous approaches on the text-to-image benchmarks and demonstrates outstanding performance on the text-to-video benchmarks.

Related papers

• RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment [10.284993431741377]
  We introduce the concept of epsilon-sample cover, which quantifies sample redundancy based on inter-sample relationships.<n>We reformulate data selection as a reinforcement learning process and propose RL-Selector.<n>Our method consistently outperforms existing state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-06-26T06:28:56Z)
• Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization [66.67988187816185]
  We aim to emphscale up the number of on-policy samples via repeated random sampling to improve alignment performance. Our experiments reveal that this strategy leads to a emphdecline in performance as the sample size increases. We introduce a scalable preference data construction strategy that consistently enhances model performance as the sample scale increases.
  arXiv  Detail & Related papers  (2025-02-24T04:22:57Z)
• Calibrated Multi-Preference Optimization for Aligning Diffusion Models [92.90660301195396]
  Calibrated Preference Optimization (CaPO) is a novel method to align text-to-image (T2I) diffusion models. CaPO incorporates the general preference from multiple reward models without human annotated data. Experimental results show that CaPO consistently outperforms prior methods.
  arXiv  Detail & Related papers  (2025-02-04T18:59:23Z)
• 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)
• Constrain Alignment with Sparse Autoencoders [45.131670081186]
  Feature-level constrained Preference Optimization is a novel method designed to simplify the alignment process while ensuring stability.<n>Our approach enjoys efficiency by using sparse features activated in a well-trained sparse autoencoder and the quality of sequential KL divergence.
  arXiv  Detail & Related papers  (2024-11-12T07:54:13Z)
• Ordinal Preference Optimization: Aligning Human Preferences via NDCG [28.745322441961438]
  We develop an end-to-end preference optimization algorithm by approxing NDCG with a differentiable surrogate loss. OPO outperforms existing pairwise and listwise approaches on evaluation sets and general benchmarks like AlpacaEval.
  arXiv  Detail & Related papers  (2024-10-06T03:49:28Z)
• General Preference Modeling with Preference Representations for Aligning Language Models [51.14207112118503]
  We introduce preference representation learning, an approach that embeds responses into a latent space to capture intricate preference structures efficiently. We also propose preference score-based General Preference Optimization (GPO), which generalizes reward-based reinforcement learning from human feedback. Our method may enhance the alignment of foundation models with nuanced human values.
  arXiv  Detail & Related papers  (2024-10-03T04:22:55Z)
• Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference [17.76565371753346]
  This paper develops two RLHF algorithms without reward inference. The key idea is to estimate the local value function difference from human preferences and then approximate the policy gradient with a zeroth-order gradient approximator. Our results show there exist provably efficient methods to solve general RLHF problems without reward inference.
  arXiv  Detail & Related papers  (2024-09-25T22:20:11Z)
• ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood [14.512464277772194]
  Aligned Supervised Fine-Tuning (ASFT) is an effective approach that better aligns Large Language Models with pair-wise datasets. ASFT mitigates the issue where the DPO loss function decreases the probability of generating human-dispreferred data. Extensive experiments demonstrate that ASFT is an effective alignment approach, consistently outperforming existing methods.
  arXiv  Detail & Related papers  (2024-09-14T11:39:13Z)
• 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. We increase the consistency and informativeness of the pairwise preference signals through targeted modifications. We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
  arXiv  Detail & Related papers  (2024-08-14T11:29:47Z)
• Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion [44.95386817008473]
  We introduce Contrastive Policy Gradient, or CoPG, a simple and mathematically principled new RL algorithm that can estimate the optimal policy even from off-policy data. We show this approach to generalize the direct alignment method IPO (identity preference optimization) and classic policy gradient. We experiment with the proposed CoPG on a toy bandit problem to illustrate its properties, as well as for finetuning LLMs on a summarization task.
  arXiv  Detail & Related papers  (2024-06-27T14:03:49Z)
• Self-Evolution Fine-Tuning for Policy Optimization [22.629113943131294]
  We introduce self-evolution fine-tuning (SEFT) for policy optimization. SEFT eliminates the need for annotated samples while retaining the stability and efficiency of supervised fine-tuning. One of the prominent features of this method is its ability to leverage unlimited amounts of unannotated data for policy optimization.
  arXiv  Detail & Related papers  (2024-06-16T06:38:02Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences. To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model. Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• Fine-Tuning Language Models with Reward Learning on Policy [68.70065254564642]
  Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. Despite its popularity, (fixed) reward models may suffer from inaccurate off-distribution. We propose reward learning on policy (RLP), an unsupervised framework that refines a reward model using policy samples to keep it on-distribution.
  arXiv  Detail & Related papers  (2024-03-28T10:02:10Z)
• Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization [165.98557106089777]
  A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets. We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
  arXiv  Detail & Related papers  (2024-02-22T04:10:57Z)
• Statistical Rejection Sampling Improves Preference Optimization [42.57245965632205]
  We introduce a novel approach to source preference data from the target optimal policy using rejection sampling. We also propose a unified framework that enhances the loss functions used in both Sequence Likelihood (SLiC) and Direct Preference Optimization (DPO) from a preference modeling standpoint.
  arXiv  Detail & Related papers  (2023-09-13T01:07:25Z)
• Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition [65.84978547406753]
  Test-time Adaptation aims to adapt the model trained on source domains to yield better predictions for test samples. Single-Utterance Test-time Adaptation (SUTA) is the first TTA study in speech area to our best knowledge.
  arXiv  Detail & Related papers  (2022-03-27T06:38:39Z)
• CAFE: Learning to Condense Dataset by Aligning Features [72.99394941348757]
  We propose a novel scheme to Condense dataset by Aligning FEatures (CAFE) At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art.
  arXiv  Detail & Related papers  (2022-03-03T05:58:49Z)
• You May Not Need Ratio Clipping in PPO [117.03368180633463]
  Proximal Policy Optimization (PPO) methods learn a policy by iteratively performing multiple mini-batch optimization epochs of a surrogate objective with one set of sampled data. Ratio clipping PPO is a popular variant that clips the probability ratios between the target policy and the policy used to collect samples. We show in this paper that such ratio clipping may not be a good option as it can fail to effectively bound the ratios. We show that ESPO can be easily scaled up to distributed training with many workers, delivering strong performance as well.
  arXiv  Detail & Related papers  (2022-01-31T20:26:56Z)

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.