Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing

• URL: http://arxiv.org/abs/2603.17942v1
• Date: Wed, 18 Mar 2026 17:14:01 GMT
• Title: Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing
• Abstract summary: Large language models (LLMs) exhibit latent multi-token prediction (MTP) capabilities despite being trained solely for next-token generation.<n>We propose a training-free MTP approach that probes an LLM using on-the-fly mask tokens drawn from its embedding space.<n>Our method constructs a speculative token tree by sampling top-K candidates from mask-token logits and applies a lightweight pruning strategy to retain high-probability continuations.
• Score: 3.861463840588074
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) exhibit latent multi-token prediction (MTP) capabilities despite being trained solely for next-token generation. We propose a simple, training-free MTP approach that probes an LLM using on-the-fly mask tokens drawn from its embedding space, enabling parallel prediction of future tokens without modifying model weights or relying on auxiliary draft models. Our method constructs a speculative token tree by sampling top-K candidates from mask-token logits and applies a lightweight pruning strategy to retain high-probability continuations. During decoding, candidate predictions are verified in parallel, resulting in lossless generation while substantially reducing the number of model calls and improving token throughput. Across benchmarks, our probing-based MTP consistently outperforms existing training-free baselines, increasing acceptance length by approximately 12\% on LLaMA3 and 8--12\% on Qwen3, and achieving throughput gains of up to 15--19\%. Finally, we provide theoretical insights and empirical evidence showing that decoder layers naturally align mask-token representations with next-token states, enabling accurate multi-step prediction without retraining or auxiliary models.

Related papers

• PriFT: Prior-Support Guided Supervised Fine-Tuning [74.65198014829393]
  Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation.<n>SFT fits fixed demonstrations token by token, including targets poorly aligned with the model's pretrained distribution.<n>We propose PriFT, which derives token weights from a frozen pretrained reference to obtain a stable reweighting signal unaffected by fine-tuning.
  arXiv  Detail & Related papers  (2026-06-08T12:14:06Z)
• AdaPonderLM: Gated Pondering Language Models with Token-Wise Adaptive Depth [23.442686851761298]
  AdaPonderLM is a self-supervised recurrent language model that learns token-wise early exiting during pretraining.<n>AdaPonderLM reduces inference compute at about 10% while maintaining comparable language modeling perplexity and competitive downstream accuracy.
  arXiv  Detail & Related papers  (2026-03-02T14:28:16Z)
• Continuous Autoregressive Language Models [56.49239051750678]
  We introduce Continuous Autoregressive Language Models (CALM)<n>CALM uses a high-fidelity autoencoder to compress a chunk of K tokens into a single continuous vector.<n>We develop a comprehensive likelihood-free framework that enables robust training, evaluation, and controllable sampling.
  arXiv  Detail & Related papers  (2025-10-31T17:58:11Z)
• Accelerating Diffusion LLMs via Adaptive Parallel Decoding [60.407727995313074]
  We introduce adaptive parallel decoding (APD), a novel method that dynamically adjusts the number of tokens sampled in parallel.<n>APD provides markedly higher throughput with minimal quality degradations on downstream benchmarks.
  arXiv  Detail & Related papers  (2025-05-31T06:10:10Z)
• L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models [95.53699156138435]
  We propose leap multi-token prediction(L-MTP), an innovative token prediction method.<n>Unlike conventional MTP, L-MTP strategically skips over intermediate tokens, predicting non-sequential ones in a single forward pass.<n>We theoretically demonstrate the benefit of L-MTP in improving inference efficiency.
  arXiv  Detail & Related papers  (2025-05-23T05:59:46Z)
• Text Generation Beyond Discrete Token Sampling [74.06071135207635]
  Mixture of Inputs (MoI) is a training-free method for autoregressive generation.<n>MoI consistently improves performance across multiple models including QwQ-32B, Nemotron-Super-49B, Gemma-3-27B, and DAPO-Qwen-32B.
  arXiv  Detail & Related papers  (2025-05-20T18:41:46Z)
• Efficient Joint Prediction of Multiple Future Tokens [20.647830092055955]
  We introduce joint multi-token prediction (JTP), a lightweight modification of standard next-token prediction.<n>Unlike previous multi-token prediction approaches, JTP strategically employs teacher forcing of future-tokens.<n>We show that the JTP approach achieves a short-horizon belief state representation, while popular alternatives for multi-token prediction fail to do so.
  arXiv  Detail & Related papers  (2025-03-24T19:52:42Z)
• FIRP: Faster LLM inference via future intermediate representation prediction [54.897493351694195]
  FIRP generates multiple tokens instead of one at each decoding step. We conduct extensive experiments, showing a speedup ratio of 1.9x-3x in several models and datasets.
  arXiv  Detail & Related papers  (2024-10-27T15:53:49Z)
• TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation [65.65530016765615]
  We propose a hierarchical predictive coding framework that captures multi-scale dependencies through three complementary learning objectives.<n> TokenUnify integrates random token prediction, next-token prediction, and next-all token prediction to create a comprehensive representational space.<n>We also introduce a large-scale EM dataset with 1.2 billion annotated voxels, offering ideal long-sequence visual data with spatial continuity.
  arXiv  Detail & Related papers  (2024-05-27T05:45:51Z)
• Better & Faster Large Language Models via Multi-token Prediction [29.067271500844928]
  Large language models such as GPT and Llama are trained with a next-token prediction loss. We suggest that training language models to predict multiple future tokens at once results in higher sample efficiency.
  arXiv  Detail & Related papers  (2024-04-30T17:33:57Z)

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.