The Viscosity of Logic: Phase Transitions and Hysteresis in DPO Alignment

• URL: http://arxiv.org/abs/2601.17260v1
• Date: Sat, 24 Jan 2026 02:19:20 GMT
• Title: The Viscosity of Logic: Phase Transitions and Hysteresis in DPO Alignment
• Abstract summary: Direct Preference Optimization (DPO) is often tuned as if increasing alignment pressure (controlled by $$) yields progressively "better" behavior.<n>We treat $$ as a control parameter and densely sweep it for three 7B open-weight families under a fixed DPO recipe.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Direct Preference Optimization (DPO) is often tuned as if increasing alignment pressure (controlled by $β$) yields progressively "better" behavior. We instead treat $β$ as a control parameter and densely sweep it for three 7B open-weight families under a fixed DPO recipe. In Mistral, capability is sharply non-monotonic: aggregated logic-probe margins become positive only in a narrow band near $β\approx 10^{-2}$ and revert outside it, with boundary points that are seed-sensitive. Across architectures under the same sweep, we observe qualitatively different response modes: sharp reorganization in Mistral, selective changes in Llama, and smooth trade-offs in Qwen. Critically, the DPO preference margin can anticorrelate with reasoning capability (Pearson $r=-0.91$ for Llama logic), so margin-based selection can prefer capability-impaired models. Training path also matters: exposure to high $β$ induces capability losses that persist even after $β$ is reduced (hysteresis). These findings motivate capability-resolved evaluation across the $β$ landscape rather than reliance on margins or aggregate benchmarks.

Related papers

• Disentangling Optimization Scale from Preference Scale in DPO [0.0]
  We show that $$ entangles two distinct roles: it governs the effective inverse preference-noise scale and simultaneously rescales the optimization dynamics.<n>We propose a centered-softplus reformulation that is argmin-equivalent to DPO for $>0$, while making the inverse preference-noise-scale and learning-rate effects explicit and independently tunable.
  arXiv  Detail & Related papers  (2026-08-27T12:21:14Z)
• Bandit Convex Optimization with Gradient Prediction Adaptivity [56.816177049016794]
  We investigate whether optimistic gradient predictions can improve worst-case regret guarantees in a prediction-adaptive manner.<n>The key idea is a novel variance-reduced gradient estimator whose variance scales with the prediction error rather than the gradient norm.<n>We establish an information-theoretic lower bound that scales as $(sqrtmathbbE[S_T])$, providing a fundamental characterization of the best achievable prediction-adaptive regret.
  arXiv  Detail & Related papers  (2026-05-21T08:57:38Z)
• $ξ$-DPO: Direct Preference Optimization via Ratio Reward Margin [16.49252561546099]
  We argue that the margin formulation in SimPO is not easily interpretable across datasets with different reward gap structures.<n>We propose $$-DPO: Direct preference optimization via ratio reward margin.
  arXiv  Detail & Related papers  (2026-05-09T03:48:16Z)
• 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)
• From $\oldsymbol{\logπ}$ to $\oldsymbolπ$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight [6.07556923512707]
  Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed a leap in Large Language Model (LLM) reasoning, yet its optimization dynamics remain fragile.<n>Standard algorithms like GRPO enforce stability via hard clipping'', which inadvertently stifles exploration by discarding gradients of tokens outside the trust region.<n>We propose Decoupled Gradient Policy Optimization (DGPO), which employs a decoupled decay mechanism based on importance sampling ratios.
  arXiv  Detail & Related papers  (2026-03-15T14:00:48Z)
• 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)
• Mitigating Mismatch within Reference-based Preference Optimization [55.07698254211876]
  Direct Preference Optimization (DPO) has become the de facto standard for offline preference alignment of large language models.<n>DPO weighs each update relative to a reference, which stabilizes the training by regularizing the updates within a trusted region.<n>This reliance becomes problematic for pessimistic pairs, where the reference model prefers the rejected response.<n>We modify DPO to treat the reference as neutral when it is pessimistic by replacing $_-_mathrmref$ with $_-max0,_mathrmref$.
  arXiv  Detail & Related papers  (2026-02-12T12:55:51Z)
• Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization [0.0]
  Margin-Adaptive Direct Preference Optimization provides a stable, data-preserving, and instance-level solution.<n>We provide a comprehensive theoretical analysis, proving that MADPO has a well-behaved optimization landscape.<n>It achieves performance gains of up to +33.3% on High Quality data and +10.5% on Low Quality data over the next-best method.
  arXiv  Detail & Related papers  (2025-10-06T20:09:37Z)
• Robust Preference Optimization via Dynamic Target Margins [35.68702558763881]
  $gamma$-PO is a dynamic target margin preference optimization algorithm.<n>It is compatible with variants of DPO that rely on reward margin between preference pairs.<n>$gamma$-PO achieves an average 4.4% improvement over other baselines.
  arXiv  Detail & Related papers  (2025-06-04T08:19:37Z)
• 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)
• RePO: Understanding Preference Learning Through ReLU-Based Optimization [66.098833436503]
  We propose ReLU-based Preference Optimization (RePO), a streamlined algorithm that eliminates $beta$ via two advances.<n>RePO is characterized as SimPO's limiting case ($beta to infty$), where the logistic weighting collapses to binary thresholding.<n> Empirical results on AlpacaEval 2 and Arena-Hard show that RePO outperforms DPO and SimPO across multiple base models.
  arXiv  Detail & Related papers  (2025-03-10T15:11:07Z)
• KL Penalty Control via Perturbation for Direct Preference Optimization [55.24971559149686]
  We propose $varepsilon$-Direct Preference Optimization ($varepsilon$-DPO), which allows adaptive control of the KL penalty strength $beta$ for each preference pair.<n> Experimental results show that the simple criterion of $varepsilon$-DPO for KL penalty relaxation significantly improves DPO compared to most existing direct alignment algorithms.
  arXiv  Detail & Related papers  (2025-02-18T06:44:10Z)
• 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)
• The Crucial Role of Samplers in Online Direct Preference Optimization [36.68862142959827]
  We provide a rigorous analysis of DPO's convergence rates with different sampling strategies under the exact gradient setting.<n>Our proposed online sampler achieves $textbfquadratic$ convergence, while uniform sampling achieves $textbflinear$ convergence.<n>For example, it outperforms vanilla DPO by over $7.4$% on Safe-RLHF dataset.
  arXiv  Detail & Related papers  (2024-09-29T07:53:50Z)
• Geometric-Averaged Preference Optimization for Soft Preference Labels [78.2746007085333]
  Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic.<n>In this work, we introduce the distributional soft preference labels and improve Direct Preference Optimization (DPO) with a weighted geometric average of the LLM output likelihood in the loss function.
  arXiv  Detail & Related papers  (2024-09-10T17:54:28Z)
• Autoregressive Bandits [58.46584210388307]
  We propose a novel online learning setting, Autoregressive Bandits, in which the observed reward is governed by an autoregressive process of order $k$. We show that, under mild assumptions on the reward process, the optimal policy can be conveniently computed. We then devise a new optimistic regret minimization algorithm, namely, AutoRegressive Upper Confidence Bound (AR-UCB), that suffers sublinear regret of order $widetildemathcalO left( frac(k+1)3/2sqrtnT (1-G
  arXiv  Detail & Related papers  (2022-12-12T21:37:36Z)

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.