Skip to content
Efficient Tool Use with Chain-of-Abstraction Reasoning episode artwork

Apr 6, 2025 21 min

Efficient Tool Use with Chain-of-Abstraction Reasoning

from Best AI papers explained Hosted by Enoch H. Kang

arXiv:2401.17464Efficient Tool Use with Chain-of-Abstraction Reasoning Silin 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.

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

Efficient Tool Use with Chain-of-Abstraction Reasoning

0:00 21:21

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of Best AI papers explained?

This episode is 21 minutes long.

When was this Best AI papers explained episode published?

This episode was published on April 6, 2025.

Can I download this Best AI papers explained episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.