Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models

• URL: http://arxiv.org/abs/2605.07783v1
• Date: Fri, 08 May 2026 14:21:05 GMT
• Title: Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models
• Abstract summary: Large language models (LLMs) achieve strong performance but remain costly to deploy in resource-constrained settings.<n>Training small language models (SLMs) from scratch is computationally expensive, while conventional knowledge distillation requires repeated access to large teachers for different target sizes.<n>We propose textbfChain-based Distillation (CBD), a scalable paradigm for efficiently initializing variable-sized language models.
• Score: 36.23126542075003
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) achieve strong performance but remain costly to deploy in resource-constrained settings. Training small language models (SLMs) from scratch is computationally expensive, while conventional knowledge distillation requires repeated access to large teachers for different target sizes, leading to poor scalability. To solve these problems, we propose \textbf{Chain-based Distillation (CBD)}, a scalable paradigm for efficiently initializing variable-sized language models. A sparse and limited sequence of intermediate models (called anchors) is constructed via stepwise distillation, forming a distillation chain that progressively transfers knowledge from the source LLMs. To support heterogeneous settings, we introduce \emph{bridge distillation} for cross-architecture and cross-vocabulary transfer. Models of variable sizes are initialized via parameter interpolation between adjacent anchors, eliminating repeated large teacher inference. Experiments show that the proposed method substantially improves efficiency and downstream performance. A 138M-parameter SLM without recovery pre-training, outperforms scratch-trained models on a 10B-token corpus on the specific task. CBD also demonstrates versatility in heterogeneous settings for initialize models with different architectures and vocabularies.

Related papers

• Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models [65.89572755202245]
  Diffusion Language Models (DLMs) offer stronger global awareness and highly parallel generation.<n>Post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient.<n>We propose a self-distilled trajectory-based post-training framework that aligns training with the easy-to-hard structure of inference.
  arXiv  Detail & Related papers  (2026-05-12T09:39:06Z)
• Model-Dowser: Data-Free Importance Probing to Mitigate Catastrophic Forgetting in Multimodal Large Language Models [2.83595986479415]
  Fine-tuning Multimodal Large Language Models (MLLMs) on task-specific data is an effective way to improve performance on downstream applications.<n>Existing methods that aim to mitigate this issue either become ineffective when fine-tuning deeper layers of the language decoder or scale poorly with increasing model size.<n>We propose Model-Dowser, a novel sparse fine-tuning approach for MLLMs.
  arXiv  Detail & Related papers  (2026-02-04T12:56:27Z)
• Theoretical Foundations of Scaling Law in Familial Models [46.506708373314375]
  We introduce Granularity (G) as a fundamental scaling variable alongside model size (N) and training tokens (D)<n>Our results reveal that the granularity penalty follows a multiplicative power law with an extremely small exponent.<n> Practically, it validates the "train once, deploy many" paradigm, demonstrating that deployment flexibility is achievable.
  arXiv  Detail & Related papers  (2025-12-29T12:01:58Z)
• Model Merging via Multi-Teacher Knowledge Distillation [11.543771846135021]
  We introduce a novel flatness-aware PAC-Bayes generalization bound specifically for the model merging setting.<n>We frame model merging as multi-teacher knowledge distillation on scarce, unlabeled data.<n>We formally demonstrate that minimizing the student-teacher Kullback-Leibler divergence directly tightens the upper bound on the merged model's excess risk.
  arXiv  Detail & Related papers  (2025-12-24T17:10:44Z)
• Model-Aware Tokenizer Transfer [46.13517417540154]
  Model-Aware Tokenizer Transfer (MATT) is a method that incorporates model internals into the tokenizer transfer process.<n>MATT introduces an Attention Influence Modeling (AIM) objective that distills inter-token communication patterns from a source model into a target model.<n>Experiments show that MATT recovers a large fraction of the original model's performance within a few GPU hours, outperforming baselines.
  arXiv  Detail & Related papers  (2025-10-24T18:27:36Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• Latent Thought Models with Variational Bayes Inference-Time Computation [52.63299874322121]
  Latent Thought Models (LTMs) incorporate explicit latent thought vectors that follow an explicit prior model in latent space.<n>LTMs demonstrate superior sample and parameter efficiency compared to autoregressive models and discrete diffusion models.
  arXiv  Detail & Related papers  (2025-02-03T17:50:34Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• Pruning Large Language Models with Semi-Structural Adaptive Sparse Training [17.381160429641316]
  Adaptive Sparse Trainer (AST) is a novel and efficient retraining framework tailored for semi-structured sparse models.<n>AST reduces the perplexity and zero-shot accuracy gap between dense and 2:4 semi-structured sparse models to 0.6 and 1.16%, respectively.
  arXiv  Detail & Related papers  (2024-07-30T06:33:44Z)
• Multi-Granularity Semantic Revision for Large Language Model Distillation [66.03746866578274]
  We propose a multi-granularity semantic revision method for LLM distillation. At the sequence level, we propose a sequence correction and re-generation strategy. At the token level, we design a distribution adaptive clipping Kullback-Leibler loss as the distillation objective function. At the span level, we leverage the span priors of a sequence to compute the probability correlations within spans, and constrain the teacher and student's probability correlations to be consistent.
  arXiv  Detail & Related papers  (2024-07-14T03:51:49Z)
• Scaling Pre-trained Language Models to Deeper via Parameter-efficient Architecture [68.13678918660872]
  We design a more capable parameter-sharing architecture based on matrix product operator (MPO) MPO decomposition can reorganize and factorize the information of a parameter matrix into two parts. Our architecture shares the central tensor across all layers for reducing the model size.
  arXiv  Detail & Related papers  (2023-03-27T02:34:09Z)

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.