用离散潜在符号压缩推理过程，提速且不丢精度。
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
- 混合使用文本和潜在符号表示推理步骤，减少输入长度。
- 在迷宫寻键、逻辑与数学题上均超越基线模型。
- 随机混入潜在符号，让模型快速适应新符号类型。
大型语言模型在链式思维（CoT）数据上训练后，能有效进行推理与规划。但这类数据的输入过长，大量词汇仅用于语义连贯性而非核心推理信息，导致计算开销巨大。本文提出一种混合表示方法：利用VQ-VAE生成的离散潜在符号，部分抽象初始推理步骤，显著缩短推理轨迹长度。我们探索了两种场景：1）从头训练模型解决钥匙寻找迷宫问题；2）在包含未见潜在符号的扩展词汇表上微调大模型，处理逻辑与数学推理任务。为促进有效学习，引入简单训练策略——随机混合潜在与文本符号，使模型能快速适应新符号。实验表明，该方法在多个基准测试中持续优于基线。
原文摘要 · Abstract (English)
Large Language Models (LLMs) excel at reasoning and planning when trained on chainof-thought (CoT) data, where the step-by-step thought process is explicitly outlined by text tokens. However, this results in lengthy inputs where many words support textual coherence rather than core reasoning information, and processing these inputs consumes substantial computation resources. In this work, we propose a hybrid representation of the reasoning process, where we partially abstract away the initial reasoning steps using latent discrete tokens generated by VQ-VAE, significantly reducing the length of reasoning traces. We explore the use of latent trace abstractions in two scenarios: 1) training the model from scratch for the Keys-Finding Maze problem, 2) fine-tuning LLMs on this hybrid data with an extended vocabulary including unseen latent tokens, for both logical and mathematical reasoning problems. To facilitate effective learning, we introduce a simple training procedure that randomly mixes latent and text tokens, which enables fast adaptation to new latent tokens. Our approach consistently outperforms the baselines methods in various benchmarks.
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。