AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders

• URL: http://arxiv.org/abs/2510.19779v1
• Date: Wed, 22 Oct 2025 17:13:00 GMT
• Title: AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders
• Authors: Yuezhou Hu, Jiaxin Guo, Xinyu Feng, Tuo Zhao,
• Abstract summary: Speculative Decoding (SD) accelerates large language model inference by employing a small draft model to generate predictions.<n> Knowledge Distillation (KD) aims to minimize the KL divergence between the draft and target models across all tokens.<n>We propose AdaSPEC, a novel method that incorporates selective token filtering into the KD process.
• Score: 36.345954548346235
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Speculative Decoding (SD) accelerates large language model inference by employing a small draft model to generate predictions, which are then verified by a larger target model. The effectiveness of SD hinges on the alignment between these models, which is typically enhanced by Knowledge Distillation (KD). However, conventional KD methods aim to minimize the KL divergence between the draft and target models across all tokens, a goal that is misaligned with the true objective of SD, which is to maximize token acceptance rate. Therefore, draft models often struggle to fully assimilate the target model's knowledge due to capacity constraints, leading to suboptimal performance. To address this challenge, we propose AdaSPEC, a novel method that incorporates selective token filtering into the KD process. AdaSPEC utilizes a reference model to identify and filter out difficult-to-fit tokens, enabling the distillation of a draft model that better aligns with the target model on simpler tokens. This approach improves the overall token acceptance rate without compromising generation quality. We evaluate AdaSPEC across diverse tasks, including arithmetic reasoning, instruction-following, coding, and summarization, using model configurations of 31M/1.4B and 350M/2.7B parameters. Our results demonstrate that AdaSPEC consistently outperforms the state-of-the-art DistillSpec method, achieving higher acceptance rates across all tasks (up to 15\%). The code is publicly available at https://github.com/yuezhouhu/adaspec.

Related papers

• Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs [63.82840470917859]
  We show that the decoding mechanism of dLLMs can be used as a powerful tool for model attribution.<n>We propose a novel information extraction scheme called the Directed Decoding Map (DDM), which captures structural relationships between decoding steps and better reveals model-specific behaviors.
  arXiv  Detail & Related papers  (2025-10-02T06:25:10Z)
• Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding [8.36763119650407]
  Speculative Verification dynamically predicts speculation accuracy and adapts the verification length to maximize throughput.<n>It improves SD performance by up to 2$times$, with an average speedup of 1.4 $times$ in large-batch settings.
  arXiv  Detail & Related papers  (2025-09-29T06:25:54Z)
• Consultant Decoding: Yet Another Synergistic Mechanism [49.996656694586164]
  Consultant Decoding (CD) verifies candidate drafts using token-level likelihoods computed solely by the large language model.<n>CD achieves up to a 2.5-fold increase in inference speed compared to the target model, while maintaining comparable generation quality.
  arXiv  Detail & Related papers  (2025-06-03T03:13:27Z)
• Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE [15.003006630308517]
  Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to predict multiple tokens.<n>We propose Jakiro, leveraging Mixture of Experts (MoE), where independent experts generate diverse predictions.<n>Our method significantly boosts prediction accuracy and achieves higher inference speedups.
  arXiv  Detail & Related papers  (2025-02-10T09:24:06Z)
• AdaEDL: Early Draft Stopping for Speculative Decoding of Large Language Models via an Entropy-based Lower Bound on Token Acceptance Probability [5.421949344085942]
  We show that AdaEDL consistently outperforms static draft-length speculative decoding by 10%-57%. We also show that AdaEDL is more robust than these techniques and preserves performance in high-temperature scenarios.
  arXiv  Detail & Related papers  (2024-10-24T01:13:43Z)
• Model Inversion Attacks Through Target-Specific Conditional Diffusion Models [54.69008212790426]
  Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to GAN's inherent flaws and biased optimization within latent space. We propose Diffusion-based Model Inversion (Diff-MI) attacks to alleviate these issues.
  arXiv  Detail & Related papers  (2024-07-16T06:38:49Z)
• DistillSpec: Improving Speculative Decoding via Knowledge Distillation [70.61777015900272]
  Speculative decoding (SD) accelerates large language model inference by employing a faster draft model for generating multiple tokens. We propose DistillSpec that uses knowledge distillation to better align the draft model with the target model, before applying SD. We show that DistillSpec yields impressive 10 - 45% speedups over standard SD on a range of standard benchmarks.
  arXiv  Detail & Related papers  (2023-10-12T16:21:04Z)
• Online Speculative Decoding [34.987825705622555]
  We introduce online speculative decoding to accelerate the inference of large language models. The main idea is to continuously update the (multiple) draft model(s) on observed user query data. We develop a prototype of online speculative decoding based on knowledge distillation and evaluate it using both synthetic and real query data.
  arXiv  Detail & Related papers  (2023-10-11T04:03:42Z)
• Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows [54.050498411883495]
  We develop a novel training method for generative models, such as Generative Adversarial Networks and Normalizing Flows. We show that achieving a specified precision-recall trade-off corresponds to minimizing a unique $f$-divergence from a family we call the textitPR-divergences. Our approach improves the performance of existing state-of-the-art models like BigGAN in terms of either precision or recall when tested on datasets such as ImageNet.
  arXiv  Detail & Related papers  (2023-05-30T10:07:17Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

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.