用内部信号实现推理步骤级验证，提升效率与准确率。
From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning
- 在每一步生成多个候选，选最一致的进行验证。
- 准确率提升3.6%，延迟降低约11%。
- 无需外部奖励模型，适合高效推理场景。
推测解码（Speculative Decoding, SD）通过轻量级草稿模型提出输出，由更强的目标模型验证以加速大语言模型推理。然而其基于标记的方法会导致错误步骤传播。先前方法依赖外部奖励模型缓解此问题，但引入额外延迟、计算开销并限制泛化能力。本文提出SpecGuard，一种仅使用模型内部信号的验证感知推测解码框架，实现步骤级验证。每一步中，SpecGuard采样多个草稿候选，选择最一致的步骤，并利用两个轻量级模型内部信号联合判断是否接受：(i) 基于注意力的定位得分，衡量对输入和已接受步骤的归属程度；(ii) 基于对数概率的置信度得分，捕捉标记级信心。二者共同决定是否接受该步骤或使用目标模型重新计算，实现计算资源的选择性分配。在多个推理基准上的实验表明，SpecGuard在提升准确率3.6%的同时，将延迟降低约11%，优于传统SD及奖励引导的SD。
原文摘要 · Abstract (English)
Speculative decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose outputs that a stronger target model verifies. However, its token-centric nature allows erroneous steps to propagate. Prior approaches mitigate this using external reward models, but incur additional latency, computational overhead, and limit generalizability. We propose SpecGuard, a verification-aware speculative decoding framework that performs step-level verification using only model-internal signals. At each step, SpecGuard samples multiple draft candidates and selects the most consistent step, which is then validated using an ensemble of two lightweight model-internal signals: (i) an attention-based grounding score that measures attribution to the input and previously accepted steps, and (ii) a log-probability-based score that captures token-level confidence. These signals jointly determine whether a step is accepted or recomputed using the target, allocating compute selectively. Experiments across a range of reasoning benchmarks show that SpecGuard improves accuracy by 3.6% while reducing latency by ~11%, outperforming both SD and reward-guided SD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。