Thinking Before You Speak: A Proactive Test-time Scaling Approach

TL;DR

This paper introduces TBYS, a proactive reasoning framework that inserts generated insights between reasoning steps in large language models to improve complex reasoning tasks, especially in mathematics.

Contribution

It proposes a novel proactive insight generation method to enhance reasoning in LLMs, reducing reliance on static prompts and human-labeled data.

Findings

Improves performance on mathematical reasoning datasets

Reduces human labeling and fine-tuning efforts

Demonstrates effectiveness over prior prompting strategies

Abstract

Large Language Models (LLMs) often exhibit deficiencies with complex reasoning tasks, such as maths, which we attribute to the discrepancy between human reasoning patterns and those presented in the LLMs' training data. When dealing with complex problems, humans tend to think carefully before expressing solutions. However, they often do not articulate their inner thoughts, including their intentions and chosen methodologies. Consequently, critical insights essential for bridging reasoning steps may be absent in training data collected from human sources. To bridge this gap, we proposes inserting \emph{insight}s between consecutive reasoning steps, which review the status and initiate the next reasoning steps. Unlike prior prompting strategies that rely on a single or a workflow of static prompts to facilitate reasoning, \emph{insight}s are \emph{proactively} generated to guide reasoning processes. We implement our idea as a reasoning framework, named \emph{Thinking Before You Speak} (TBYS), and design a pipeline for automatically collecting and filtering in-context examples for the generation of \emph{insight}s, which alleviates human labeling efforts and fine-tuning overheads. Experiments on challenging mathematical datasets verify the effectiveness of TBYS. Project website: https://gitee.com/jswrt/TBYS