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.

翻译：大型语言模型虽仅以生成下一个token为训练目标，却展现出隐式的多token预测能力。我们提出一种简单且无需训练的MTP方法，该方法通过在嵌入空间中实时提取掩码token来探测模型，从而并行预测未来token，无需修改模型权重或依赖辅助草稿模型。本方法通过从掩码token的logit中采样Top-K候选方案构建推测性token树，并采用轻量级剪枝策略保留高概率延续序列。解码时，候选预测结果并行验证，在保证无损生成的同时显著减少模型调用次数并提升token吞吐量。在多项基准测试中，基于探测的MTP方法始终优于现有免训练基线，在LLaMA3上使接受长度提升约12%，在Qwen3上提升8-12%，吞吐量提升高达15-19%。最后，我们通过理论分析和实验证据表明，解码器层自然地将掩码token表示与下一个token状态对齐，从而无需重新训练或辅助模型即可实现准确的多步预测。