SMOPD: Selective Token-Entropy Masking for Dirty-History Multi-Turn On-Policy Self-Distillation

• URL: http://arxiv.org/abs/2608.14647v1
• Date: Thu, 30 Jul 2026 08:40:30 GMT
• Title: SMOPD: Selective Token-Entropy Masking for Dirty-History Multi-Turn On-Policy Self-Distillation
• Abstract summary: We introduce SMOPD (Selective Masking for On-Policy Distillation), a loss-only stabilization method for multi-turn OPSD.<n>For each generated middle-turn reply, SMOPD ranks token positions by student entropy and removes the lowest-entropy 20% from the clipped generalized Jensen-Shannon distillation loss.<n>This design targets token-level uncertainty rather than coarse trajectory outcomes, adds no parameters, and has zero inference-time overhead.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dirty-history rollouts make multi-turn on-policy self-distillation (OPSD) brittle: once a student emits an erroneous intermediate reply, later turns are conditioned on that reply, and uniform distillation can spend loss on tokens that carry little corrective signal. We introduce SMOPD (Selective Masking for On-Policy Distillation), a loss-only stabilization method for multi-turn OPSD. For each generated middle-turn reply, SMOPD ranks token positions by student entropy and removes the lowest-entropy 20% from the clipped generalized Jensen-Shannon distillation loss; final-answer and FULL-preservation losses are unchanged. This design targets token-level uncertainty rather than coarse trajectory outcomes, adds no parameters, and has zero inference-time overhead. We compare SMOPD with a correctness-scaling variant that multiplies a common detached reliability proxy using final-answer correctness. On LiC with Qwen3 models, SMOPD improves SHARDED-view accuracy by 1.0-2.5 percentage points in single-seed 1.7B, 4B, and 8B comparisons, and a small 4B multi-seed check shows a +1.7pp mean SHARDED gain over baseline (two-tailed p = 0.022). Adding the outcome scalar is harmful without masking at 1.7B (-4.0pp) and remains scale-dependent when combined with masking (+1.3pp at 4B, neutral at 1.7B, and -0.5pp at 8B). These archived aggregate results suggest that token-level uncertainty is a more reliable stabilization signal than scalar final-answer correctness in this evaluated dirty-history OPSD setting, while leaving causal mechanism tests and broader benchmark validation to future work.

Related papers

• WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training [48.290951447286744]
  WDL-OPD is a mixture-constrained co-training method with two trainable policies.<n>An anchor policy generates every rollout, an auxiliary policy evaluates the same visited states, and a geometric mixture of their token distributions is matched to a frozen teacher by reverse KL.<n>We show that freezing the auxiliary recovers an anchor-plus-contrast proxy target closely related to OPD$2$ and W2S-OPD, whereas joint training creates branch-level degrees of freedom that a static delta cannot express.
  arXiv  Detail & Related papers  (2026-08-10T11:22:53Z)
• Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training [51.18425726646089]
  We propose textscSURE, a unified latent-space framework for image and video diffusion models.<n>It learns reward distributions and directly uses their reliability to guide dense post-training.<n>textscSURE-REFL achieves the highest VBench quality, semantic, and total scores among the evaluated methods.
  arXiv  Detail & Related papers  (2026-08-06T14:55:42Z)
• Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance [0.6768558752130311]
  We analyze Diffusion-free guidance (CFG) through an integrator-analysis lens.<n>We show that guidance re-stiffens exactly the discriminative subspace to an anomalous 1+w.<n> DDIM is no longer fitted there, and on coarse meshes its guided residual diverges as sigma_min goes zero.
  arXiv  Detail & Related papers  (2026-07-08T17:21:51Z)
• Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning [36.34371525731833]
  We introduce the Independent Combinatorial Tokens (ICT) framework, which shifts the optimization focus from scalar uncertainty to the distributional properties of token logits.<n>Our theoretical analysis, grounded in both Shannon and second-order Rényi entropy, proves that selectively updating on these tokens regulates policy concentration.<n> Empirical results demonstrate that updating only the top 10% of unique tokens on Qwen2.5 (0.5B/1.5B/7B) models yields an average pass@4 improvement of 4.58%, with a maximum gain of 14.9%, over GRPO, 20-Entropy, and STAPO baselines.
  arXiv  Detail & Related papers  (2026-06-18T04:11:56Z)
• The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs [52.709361620508595]
  ListOPD brings a student to in-domain with an 8B-SFT baseline at one-fifth the parameters.<n>On Amazon Fashion, three pre-registered tests--a fine-grid cliff interval test, and a small-clip cross-prediction--fall within their locked prediction windows--with the small-clip value matching the closed-form prediction below grid resolution.
  arXiv  Detail & Related papers  (2026-05-09T06:48:00Z)
• Low-Rank Adaptation Reduces Catastrophic Forgetting in Sequential Transformer Encoder Fine-Tuning: Controlled Empirical Evidence and Frozen-Backbone Representation Probes [3.305265383862785]
  We present an empirical study of Low-Rank Adaptation (LoRA) in sequential transformer encoder finetuning with companion representation probes.<n>In five full-validation BERT-base reruns on an RTE->MRPC->CoLA->SST-2 sequence, full fine-tuning yields 19.9% +/- average forgetting, whereas standard LoRA (r, query/value modules) yields 0.6% +/-1.4%.
  arXiv  Detail & Related papers  (2026-03-29T14:14:36Z)
• When Does Margin Clamping Affect Training Variance? Dataset-Dependent Effects in Contrastive Forward-Forward Learning [0.0]
  Contrastive Forward-Forward (CFF) learning trains Vision Transformers layer by layer against supervised contrastive objectives.<n>We focus on one implementation detail: the positive-pair margin in the contrastive loss is applied through saturating similarity clamping.<n>We prove that an alternative formulation, subtracting the margin after the log-probability, is gradient-neutral under the mean-over-positives reduction.
  arXiv  Detail & Related papers  (2026-03-01T07:00:38Z)
• Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning [17.384089089363382]
  We identify a root cause that existing methods overlook: the uniform penalization of errors.<n>Current approaches treat all incorrect rollouts within a group identically.<n>We propose the Asymmetric Confidence-aware Error Penalty (ACE)
  arXiv  Detail & Related papers  (2026-02-24T22:46:43Z)
• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization [85.50560211492898]
  Test-time adaptation (TTA) may fail to improve or even harm the model performance when test data have mixed distribution shifts.<n>This is often a key obstacle preventing existing TTA methods from being deployed in the real world.<n>We propose a sharpness-aware and reliable entropy minimization method, called SAR, for stabilizing TTA from two aspects.
  arXiv  Detail & Related papers  (2025-09-05T10:03:00Z)
• Robust Fine-tuning of Zero-shot Models via Variance Reduction [56.360865951192324]
  When fine-tuning zero-shot models, our desideratum is for the fine-tuned model to excel in both in-distribution (ID) and out-of-distribution (OOD) We propose a sample-wise ensembling technique that can simultaneously attain the best ID and OOD accuracy without the trade-offs.
  arXiv  Detail & Related papers  (2024-11-11T13:13:39Z)

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.