通过时间维度对比提升大模型生成质量，计算开销极低。
Temporal Guidance for Large Language Models
- 利用多标记预测构建模型自对比，沿时间轴设计新策略
- 在多个模型和基准上显著提升性能，额外内存与计算开销极小
- 适合追求高效高质量生成的开发者与研究者
对比解码（CD）能提升大语言模型（LLM）的生成质量，但需依赖辅助模型，带来显著计算开销。现有内部自对比解码方法如基于层间差异的DoLa，在小规模模型上表现不稳定。本文观察到LLM存在局部偏好，提出一种沿时间维度的新对比引导策略——时间引导（TeGu）。该方法巧妙利用多标记预测（MTP）构建较弱的自我预测作为对比基线。为标准化实现，进一步引入轻量级条件MTP投影器（cMTPP），避免维护多个独立网络。在多种模型系列与基准测试中，TeGu在保持极低额外内存和计算开销的前提下，实现了显著的性能提升。
原文摘要 · Abstract (English)
Contrastive Decoding (CD) enhances the generation quality of large language models (LLMs) but incurs significant additional computational overhead due to the need for an auxiliary model. Existing internal self-contrastive decoding methods, such as Decoding by Contrasting Layers (DoLa), focus on discrepancies across different layers, which are notably unstable on small-scale models. In this work, based on the observation that LLMs exhibit local preferences, we propose a novel contrastive guidance strategy along the temporal dimension, namely Temporal Guidance (TeGu). Our method ingeniously leverages Multi-Token Prediction (MTP) to construct weaker amateur predictions for model self-contrast. To standardize the implementation of this mechanism, we further introduce a lightweight Conditional MTP Projector (cMTPP), which avoids maintaining multiple independent networks as required by other MTP modules. Across various model series and benchmarks, TeGu achieves significant performance improvements while maintaining low additional memory consumption and computational overhead.
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。