DemoPSD: Disagreement-Modulated Policy Self-Distillation

• URL: http://arxiv.org/abs/2607.02502v2
• Date: Mon, 06 Jul 2026 11:02:57 GMT
• Title: DemoPSD: Disagreement-Modulated Policy Self-Distillation
• Abstract summary: On-policy self-distillation has emerged as a practical method for training large language models.<n>DemoPSD steers the student toward a weighted geometric combination of the teacher and student distributions.
• Score: 49.30809363804017
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access. However, recent studies have found that the teacher's dense token-level supervision, conditioned on privileged information, can lead to overfitting to in-domain patterns, suppress exploration, and hurt cross-domain generalization, while also introducing a more fundamental issue: *privileged information leakage*, where the student encodes answer-dependent shortcuts that are unavailable at test time. We introduce **DemoPSD**, a novel framework that resolves such problems through the idea of *selective adoption of teacher guidance*. Instead of fitting the full teacher distribution, DemoPSD steers the student toward a *reverse-KL barycenter target*, a weighted geometric combination of the teacher and student distributions, that naturally balances learning from the teacher with preserving the student's own reasoning capacity. We measure the difference between their distributions and use such a discrepancy to adaptively control the blending at each token position. We provably show that DemoPSD achieves **(1)** *leakage attenuation*, i.e., effective mitigation of privileged information leakage; and **(2)** *exploration preservation*, i.e., preservation of exploration capacity under dense token-level distillation. Extensive experiments on SciKnowEval across four scientific fields show that DemoPSD outperforms both GRPO and SDPO while maintaining higher training entropy and robustly generalizing to out-of-distribution GPQA benchmarks.

Related papers

• Contrastive On-Policy Distillation [36.47487086937924]
  We propose COPD, a contrastive On-policy Distillation framework.<n> COPD directly encourages the student model to learn more concise and efficient reasoning strategies.
  arXiv  Detail & Related papers  (2026-07-21T12:35:04Z)
• dOPSD: On-Policy Self-Distillation for Diffusion Language Models [52.60302464420127]
  Diffusion large language models generate text by iteratively denoising a masked sequence.<n>Supervised fine-tuning is off-policy and suffers from exposure bias, while reinforcement learning gives only sparse, sequence-level rewards.<n>On-policy self-distillation (OPSD) offers a promising alternative, using one model as both student and teacher.
  arXiv  Detail & Related papers  (2026-07-05T17:47:29Z)
• DOPD: Dual On-policy Distillation [59.65986569617147]
  On-policy distillation offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals.<n>We propose DOPD, an advantage-aware dual distillation paradigm that dynamically routes token-level supervision between privileged teacher and privileged student policies.<n>Experiments on both large language model (LLM) and vision-language model (VLM) settings demonstrate that DOPD consistently outperforms Vanilla OPD.
  arXiv  Detail & Related papers  (2026-06-29T17:55:53Z)
• EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation [5.310892696470208]
  On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm.<n>The challenge in this approach is that the privileged information can change model behavior more than intended.<n>We propose EviDence GuidEd On-Policy Distillation (EDGE-OPD), a modification of OPD with two distinct characteristics.
  arXiv  Detail & Related papers  (2026-05-22T10:55:15Z)
• Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning [41.384652481442735]
  We propose textbfDirection-Adaptive Self-Distillation (textbfDASD), which reframes privileged self-distillation from uniform teacher imitation into entropy-routed directional supervision.<n>Across six mathematical reasoning benchmarks, DASD achieves the best macro Avg@16 over strong RLVR and self-distillation baselines.
  arXiv  Detail & Related papers  (2026-05-21T10:07:46Z)
• Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation [49.117085054884676]
  On-policy distillation trains a student model on its own rollouts using dense feedback from a stronger teacher.<n>We operationalize this principle through a trajectory-specific release rule.<n> Experimental results across strong-to-weak distillation tasks indicate that this release rule consistently outperforms standard full-trajectory OPD.
  arXiv  Detail & Related papers  (2026-05-13T15:05:30Z)
• The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes [10.319573084070578]
  On-policy distillation (OPD) and on-policy self-distillation (OPSD) have emerged as promising post-training methods for large language models.<n>We present a comprehensive empirical study of when OPD and OPSD work, when they fail, and why.
  arXiv  Detail & Related papers  (2026-05-11T19:44:59Z)
• TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents [55.27396165691312]
  We identify a key limitation of vanilla OPD in multi-turn agent settings, which we term Trajectory-Level KL Instability.<n>We propose TCOD, a framework that controls the trajectory depth exposed to the student and progressively expands it with a curriculum schedule.<n> Experimental results across four student-teacher pairs show that TCOD mitigates KL escalation and enhances KL stability throughout training, improving agent performance by up to 18 points over vanilla OPD.
  arXiv  Detail & Related papers  (2026-04-27T03:38:27Z)
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models [44.041109669153506]
  On-Policy Self-Distillation (OPSD) is a framework where a single model acts as both teacher and student by conditioning on different contexts.<n>We demonstrate the efficacy of our method on multiple mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-01-26T17:56:50Z)
• ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $α$-$β$-Divergence [89.630486749083]
  Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student model.<n>The core challenge in KD lies in balancing two mode-concentration effects.<n>We propose ABKD, a generic framework with $alpha$$beta$-divergence.
  arXiv  Detail & Related papers  (2025-05-07T16:48:49Z)

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.