Token Assorted：混合潜在Token与文本Token以提升语言模型推理能力
Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
AI总结：
针对大语言模型思维链推理输入冗长、计算成本高的问题，提出用VQ-VAE生成的潜在离散Token与文本Token混合表示推理过程的方法，通过随机混合训练策略适配新Token，在多类推理任务基准上优于基线。
摘要：
大语言模型（LLM）在基于思维链（CoT）数据训练时，在推理与规划任务上表现优异，这类数据会通过文本Token明确呈现逐步思考过程。但这会导致输入序列过长，其中大量词汇仅用于维持文本连贯性而非承载核心推理信息，处理这些输入会消耗大量计算资源。本研究提出一种推理过程的混合表示方法，利用VQ-VAE生成的潜在离散Token对初始推理步骤进行部分抽象，大幅缩短推理轨迹的长度。我们在两种场景下探索潜在轨迹抽象的应用：一是针对Keys-Finding Maze问题从头训练模型；二是在包含未见过的潜在Token的扩展词表下，用这种混合数据微调LLM，以解决逻辑推理与数学推理问题。为实现有效学习，我们提出一种简单的训练流程：随机混合潜在Token与文本Token，使模型能快速适配新的潜在Token。在多个基准测试中，我们的方法性能始终优于基线方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
