The paper investigates how the optimal teacher model size for knowledge distillation changes with the amount of training data. It finds that when data is scarce, smaller teachers can outperform larger ones, a phenomenon driven by both score geometry and relational ordering of class predictions. The authors propose DVA, a data‑selection method that uses a small teacher to filter samples by difficulty and maximize diverse relational signals, achieving competitive results without relying on training dynamics.
arXiv:2608. 13721v1 Announce Type: cross Abstract: In reasoning supervised fine-tuning, candidate responses for the same instruction can differ substantially in how well they match the student's current distribution.
arXiv:2402. 14035v4 Announce Type: replace-cross Abstract: Knowledge distillation from foundation models to compact domain models is challenging due to substantial gaps in capacity, architecture, and modality.
The paper presents a method for distilling tabular foundation models (TFMs) into lightweight, dataset‑specific students. By using the full labeled training set as teacher context and training students on both observed and synthetic queries, the authors achieve significant performance gains over traditional supervised models on TabArena and TALENT benchmarks. The distilled students also provide substantial inference speedups, reducing the cost of repeated inference.
arXiv:2606. 25488v1 Announce Type: new Abstract: Knowledge Distillation (KD) is widely used to obtain compact models for efficient inference in resource-constrained environments.
arXiv:2609.14193v1 Announce Type: cross Abstract: On-policy distillation (OPD) has become a standard component of frontier post-training pipelines, yet how much its training data actually contributes...
The paper investigates data efficiency and selection in On‑Policy Distillation (OPD) for large language models. It shows that 1‑shot OPD—training on a single example—consistently improves performance, especially when the example is hard, and that longer chain‑of‑thought (CoT) paths drive the gains rather than token entropy. Based on these findings, the authors propose a simple hard‑example selection strategy that, using only eight carefully chosen hard examples, matches the performance of a 17,000‑example baseline across models from 1.5B to 7B parameters.
Large language models (LLMs) achieve strong performance across many tasks, but their high computational cost limits deployment in resource-constrained environments. Knowledge Distillation (KD) offers a practical solution by transferring knowledge from a teacher model of a larger size to a smaller student model.
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...
Compact instruction-following rerankers are attractive for deployment, but conventional distillation pipelines typically train students by offline imitation of teacher outputs on a fixed set of exampl...
The paper introduces a two‑stage training framework for compact instruction‑following rerankers. Stage 1 strengthens a 4B teacher reranker with off‑policy GRPO using LLM‑judge feedback on 88K examples, while Stage 2 trains a 1B student by sampling its own rankings and receiving soft teacher‑derived rewards, blending exploration with knowledge transfer. The method achieves superior nDCG and MRR scores on MAIR‑11 and MAIR‑Full benchmarks, outperforming offline distillation baselines and larger RL‑trained rerankers.
arXiv:2608. 04419v1 Announce Type: cross Abstract: On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but standard reverse-KL training can assign insufficient probability to other plausible continuations.
arXiv:2608. 08176v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) improves the reasoning abilities of LLMs by internalizing privileged context into model parameters through self-distillation.