Efficient Tool Use with Chain-of-Abstraction Reasoning

arXiv:2401.17464Efficient Tool Use with Chain-of-Abstraction ReasoningSilin Gao, Jane Dwivedi-Yu, Ping Yu, Xiaoqing Ellen Tan, Ramakanth Pasunuru, Olga Golovneva, Koustuv Sinha, Asli Celikyilmaz, Antoine Bosselut, Tianlu WangThis research paper introduces Chain-of-Abstraction (CoA), a novel method designed to enhance the ability of large language models (LLMs) to effectively utilize external tools for complex, multi-step reasoning. CoA trains LLMs to first generate abstract reasoning chains with placeholders, which are then filled with specific knowledge obtained from external tools like search engines or calculators. This approach allows LLMs to learn more general reasoning strategies that are less dependent on specific factual knowledge and enables parallel processing of reasoning and tool use, leading to faster inference speeds. Evaluations in mathematical reasoning and Wikipedia question answering demonstrate that CoA outperforms existing methods, yielding higher accuracy and more efficient tool utilization.