Guiding Language Model Math Reasoning with Planning Tokens
CoRR(2023)
摘要
Large language models (LLMs) have recently attracted considerable interest
for their ability to perform complex reasoning tasks, such as chain-of-thought
reasoning. However, most of the existing approaches to enhance this ability
rely heavily on data-driven methods, while neglecting the structural aspects of
the model's reasoning capacity. We find that while LLMs can manage individual
reasoning steps well, they struggle with maintaining consistency across an
entire reasoning chain. To solve this, we introduce planning tokens at the
start of each reasoning step, serving as a guide for the model, and add their
embeddings to the model parameters. Our approach requires a negligible increase
in trainable parameters (just 0.001
fine-tuning or a more parameter-efficient scheme. We demonstrate our method's
effectiveness by applying it to three different LLMs, showing notable accuracy
improvements across three math word problem datasets w.r.t. standard
fine-tuning baselines.
更多查看译文
关键词
language model reasoning,planning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要