面向语言建模的思考令牌（Thinking Tokens）
Thinking Tokens for Language Modeling
AI总结：
针对语言模型复杂计算与推理能力不足的问题，研究者提出引入特殊的thinking tokens（思考令牌），类比人类思考过程让模型在处理复杂问题时执行更多计算，以此提升泛化能力。
摘要：
56乘以37等于多少？语言模型在这类复杂计算中经常出错，这通常被归因于它们无法进行复杂推理。由于语言模型依赖大规模训练集和强大的记忆能力，天然不具备执行复杂计算的能力。不过可以认为，人类也无法立刻算出这道题，需要相当长的时间来构建解题过程。为了提升语言模型的泛化能力，同时类比人类的思考行为，我们提出使用特殊的“thinking tokens（思考令牌）”，让模型在遇到复杂问题时能够执行多得多的计算步骤。
英文摘要：
How much is 56 times 37? Language models often make mistakes in these types of difficult calculations. This is usually explained by their inability to perform complex reasoning. Since language models rely on large training sets and great memorization capability, naturally they are not equipped to run complex calculations. However, one can argue that humans also cannot perform this calculation immediately and require a considerable amount of time to construct the solution. In order to enhance the generalization capability of language models, and as a parallel to human behavior, we propose to use special 'thinking tokens' which allow the model to perform much more calculations whenever a complex problem is encountered.
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。
