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

ACL ARR 2025 May Submission964 Authors

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 the solutions. However, they often do not articulate their inner thoughts that involve their intentions, chosen methodologies, etc. Consequently, in training data collected from human sources, critical insights essential for bridging reasoning steps may be absent. 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. \emph{Source code attached will be released upon publication.}

Paper Type: Short

Research Area: Language Modeling

Research Area Keywords: Proactive Test-time Scaling, Bridging Reasoning Gap, Automatically Data Collecting and Filtering

Contribution Types: NLP engineering experiment

Languages Studied: English

Keywords: Proactive Test-time Scaling, Bridging Reasoning Gap, Automatically Data Collecting and Filtering

Submission Number: 964