$ξ$-DPO: Direct Preference Optimization via Ratio Reward Margin

• URL: http://arxiv.org/abs/2605.10981v1
• Date: Sat, 09 May 2026 03:48:16 GMT
• Title: $ξ$-DPO: Direct Preference Optimization via Ratio Reward Margin
• Abstract summary: We argue that the margin formulation in SimPO is not easily interpretable across datasets with different reward gap structures.<n>We propose $$-DPO: Direct preference optimization via ratio reward margin.
• Score: 16.49252561546099
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reference-free preference optimization has emerged as an efficient alternative to reinforcement learning from human feedback, with Simple Preference Optimization(SimPO) demonstrating strong performance by eliminating the explicit reference model through a simple objective. However, the joint tuning of the hyperparameters $β$ and $γ$ in SimPO remains a central challenge. We argue that this difficulty arises because the margin formulation in SimPO is not easily interpretable across datasets with different reward gap structures. To better understand this issue, we conduct a comprehensive analysis of SimPO and find that $β$ implicitly controls sample filtering, while the effect of $γ$ depends on the reward gap structure of the dataset. Motivated by these observations, we propose $ξ$-DPO: Direct preference optimization via ratio reward margin. We first reformulate the preference objective through an equivalent transformation, changing the optimization target from maximizing the likelihood of reward gaps to minimizing the distance between reward gaps and optimal margins. Then, we redefine the reward in a ratio form between the chosen and rejected, which effectively cancels the effect of $β$ and yields a bounded and interpretable margin. This margin is called the ratio reward margin and is denoted by $ξ$. Unlike the margin $γ$ in SimPO, $ξ$ explicitly represents the desired relative separation between chosen and rejected responses and can be determined from the initial reward gap distribution, avoiding repeated trial-and-error tuning. ....

Related papers

• Disentangling Optimization Scale from Preference Scale in DPO [0.0]
  We show that $$ entangles two distinct roles: it governs the effective inverse preference-noise scale and simultaneously rescales the optimization dynamics.<n>We propose a centered-softplus reformulation that is argmin-equivalent to DPO for $>0$, while making the inverse preference-noise-scale and learning-rate effects explicit and independently tunable.
  arXiv  Detail & Related papers  (2026-08-27T12:21:14Z)
• Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization [60.89431018071735]
  Reinforcement learning with group-relative advantages has become the de facto standard for post-training language model reasoners.<n>We show that rollouts with distinct reward profiles can receive identical advantages, and all objectives are optimized with fixed relative weights regardless of their current level of saturation.<n>We introduce saturation-aware reweighting, which standardizes each reward objective independently and adaptively discounts its contribution according to a batch-level estimate of objective saturation.
  arXiv  Detail & Related papers  (2026-08-17T04:07:50Z)
• Reward Learning from Best-of-$N$ Preference Data: Targets, Tradeoffs, and Design Principles [39.21477667267936]
  We specialize a recent analysis of preference data via its induced conditional distribution to Best-of-$N$.<n>For independent-reference variants, we derive closed-form reward targets as explicit functions of $N$ and the base distribution.<n>Experiments on synthetic and real preference data support the predicted dependence on sample size and base-distribution shape.
  arXiv  Detail & Related papers  (2026-05-28T22:15:57Z)
• Bandit Convex Optimization with Gradient Prediction Adaptivity [56.816177049016794]
  We investigate whether optimistic gradient predictions can improve worst-case regret guarantees in a prediction-adaptive manner.<n>The key idea is a novel variance-reduced gradient estimator whose variance scales with the prediction error rather than the gradient norm.<n>We establish an information-theoretic lower bound that scales as $(sqrtmathbbE[S_T])$, providing a fundamental characterization of the best achievable prediction-adaptive regret.
  arXiv  Detail & Related papers  (2026-05-21T08:57:38Z)
• Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders [74.55181072260713]
  Training with beam-search negatives consistently outperforms random negatives.<n>We introduce Windowed Partial AUC (WPAUC), which constrains the false positive rate (FPR) to a window to more directly align with Top-$K$ metrics.<n>Experiments on four real-world datasets validate the theory and deliver consistent state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-04-24T12:31:57Z)
• Reinforcement Learning from Multi-Source Imperfect Preferences: Best-of-Both-Regimes Regret [71.69884486156359]
  We study episodic RL from emphmulti-source imperfect preferences through a cumulative imperfection budget.<n>We propose a unified algorithm with regret $tildeO(sqrtK/M+)$, which exhibits a best-of-both-regimes behavior.
  arXiv  Detail & Related papers  (2026-03-20T19:34:53Z)
• FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA [68.44043212834204]
  Low-Rank Adaptation (LoRA) is widely used for efficient fine-tuning of language models in learning (FL)<n>Low-Rank Adaptation (LoRA) is widely used for efficient fine-tuning of language models in learning (FL)
  arXiv  Detail & Related papers  (2025-05-19T07:32:56Z)
• Multi-Preference Optimization: Generalizing DPO via Set-Level Contrasts [17.243429150450886]
  We propose $textbfMulti-Preference Optimization (MPO) to optimize over entire sets of responses.<n>MPO employs deviation-based weighting, which emphasizes outlier responses that deviate most from the mean reward.<n>We theoretically prove that MPO reduces alignment bias at a rate of $mathcalOleft(frac1sqrtnright)$ with respect to the number of responses per query.
  arXiv  Detail & Related papers  (2024-12-05T21:50:22Z)
• 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)
• 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.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>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)
• $i$REPO: $i$mplicit Reward Pairwise Difference based Empirical Preference Optimization [12.266207199002604]
  Large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. We propose a novel framework named $i$REPO, which utilizes implicit Reward pairwise difference regression for Empirical Preference Optimization. We show that $i$REPO effectively achieves self-alignment using soft-label, self-generated responses and the logit of empirical AI annotators.
  arXiv  Detail & Related papers  (2024-05-24T05:42:11Z)
• Vector Optimization with Stochastic Bandit Feedback [10.66048003460524]
  We introduce vector optimization problems with geometric bandit feedback. We consider $K$ designs, with multi-dimensional mean reward vectors, which are partially ordered according to a polyhedral ordering cone $C$.
  arXiv  Detail & Related papers  (2021-10-23T22:38:54Z)

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.