Teaching Algorithmic Reasoning via In-context Learning

Hattie Zhou, Azade Nova, Aaron Courville, Hugo Larochelle, Behnam Neyshabur, Hanie Sedghi

Keywords: in-context learning, algorithmic reasoning, LLMs, prompting

TL;DR: We study how to teach algorithmic reasoning to LLMs via in-context learning. We show that algorithmic reasoning can be taught by increasing specificity in the way we explain the steps of an algorithm along with running examples.

Abstract: Large language models (LLMs) have shown increasing in-context learning capabilities through scaling up model and data size. Despite this progress, LLMs are still unable to solve algorithmic reasoning problems. While providing a rationale with the final answer has led to further improvements in multi-step reasoning problems, Anil et al. 2022 showed that even simple algorithmic reasoning tasks such as parity are far from solved. In this work, we identify and study four key stages for successfully teaching algorithmic reasoning to LLMs: (1) formulating algorithms as skills, (2) teaching multiple skills simultaneously (skill accumulation), (3) teaching how to combine skills (skill composition) and (4) teaching how to use skills as tools. We show that it is possible to teach algorithmic reasoning to LLMs via in-context learning, which we refer to as Algorithmic Prompting. We evaluate our approach on a variety of arithmetic and quantitative reasoning tasks, and demonstrate significant boosts in performance over existing prompting techniques. In particular, for long parity, addition, multiplication and subtraction and parity tasks, we achieve an error reduction of approximately 10x, 9x, 5x and 2x respectively compared to the best available baselines.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning