Tab-CoT: Zero-shot Tabular Chain of Thought

TL;DR

Tab-CoT introduces a structured tabular prompting method that explicitly models complex reasoning processes in a highly organized manner, enhancing zero-shot and few-shot performance across diverse reasoning tasks.

Contribution

It presents a novel tabular-format CoT prompting technique that explicitly captures multi-dimensional reasoning, improving interpretability and effectiveness in NLP tasks.

Findings

Effective in zero-shot and few-shot settings.

Capable of reasoning across multiple dimensions (rows and columns).

Shows strong performance on various reasoning tasks.

Abstract

The chain-of-though (CoT) prompting methods were successful in various natural language processing (NLP) tasks thanks to their ability to unveil the underlying complex reasoning processes. Such reasoning processes typically exhibit implicitly structured steps. Recent efforts also started investigating methods to encourage more explicitly structured reasoning procedures to be captured. In this work, we propose Tab-CoT, a novel tabular-format CoT prompting method, which allows the complex reasoning process to be explicitly modelled in a highly structured manner. Despite its simplicity, we show that our approach is capable of performing reasoning across multiple dimensions (i.e., both rows and columns). We demonstrate our approach's strong zero-shot and few-shot capabilities through extensive experiments on a range of reasoning tasks.