arXiv:2606. 12171v1 Announce Type: cross Abstract: Knowledge Distillation (KD) and mixup have proven effective at inducing smoothness in class boundaries; KD captures inherent class relationships in probability distributions, and mixup enforces them through convex combinations of inputs.
Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which account for 63. 0-68.
arXiv:2608. 09826v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which account for 63.
arXiv:2609.36734v1 Announce Type: new Abstract: Knowledge Distillation (KD) trains a smaller-capacity student model to imitate a larger-capacity teacher model by matching output distributions, implic...
arXiv:2605.28791v2 Announce Type: replace-cross Abstract: On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes in...
arXiv:2609.01532v1 Announce Type: new Abstract: Logit-based knowledge distillation (KD) is used to train smaller language models (LMs) via supervision from stronger teachers, but whether its benefits...
arXiv:2608. 14728v1 Announce Type: cross Abstract: On-policy distillation (OPD) has emerged as an effective paradigm for transferring knowledge between language models, where a student is trained to align its next-token distribution with the teacher's along its own trajectories.
arXiv:2609.13199v1 Announce Type: new Abstract: Knowledge distillation aims to improve the performance of lightweight student models by transferring knowledge from larger and more powerful teacher mo...
arXiv:2609.17474v1 Announce Type: cross Abstract: Large language model (LLM) distillation aims to transfer the capabilities of a powerful teacher to a smaller student. Direct imitation, however, can...
The paper introduces Preference‑Based Self‑Distillation (PBSD), a new on‑policy self‑distillation method that replaces traditional KL matching with a reward‑regularized objective. PBSD derives a reward‑reweighted teacher distribution, optimizing preference gaps between teacher and student samples while keeping on‑policy sampling. Experiments on mathematical reasoning and tool‑use tasks show PBSD achieves stronger average performance, improved training stability, and maintains token efficiency compared to prior self‑distillation baselines.
arXiv:2607. 17247v1 Announce Type: cross Abstract: Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment.
The paper investigates how the sampled-token reverse-KL loss in on‑policy distillation distributes updates across tokens. By analyzing the gradient of the per‑token K2 estimator, the authors find that tokens with low student probability and large teacher‑student gaps receive disproportionately large gradient norms. They propose Surprise‑aware Reweighting (SuRe), a lightweight weighting rule that further amplifies this allocation, and demonstrate that SuRe improves math metrics on Qwen3 student models without harming out‑of‑domain performance.