CCQA: Generating Question from Solution Can Improve Inference-Time Reasoning in SLMs
This addresses the challenge of enhancing reasoning accuracy in SLMs, which is an incremental improvement over prior methods for efficient AI applications.
The paper tackles the problem of improving inference-time reasoning in small language models (SLMs) by proposing CCQA, a cycle-consistency method that generates questions from reasoning paths and selects solutions based on similarity, which consistently outperforms existing SOTA methods across eight models on mathematical and commonsense reasoning benchmarks.
Recently, inference-time reasoning strategies have further improved the accuracy of large language models (LLMs), but their effectiveness on smaller models remains unclear. Based on the observation that conventional approaches often fail to improve performance in this context, we propose \textbf{C}ycle-\textbf{C}onsistency in \textbf{Q}uestion \textbf{A}nswering (CCQA), a novel reasoning method that can be effectively applied to SLMs. Inspired by cycle consistency, CCQA generates a question from each reasoning path and answer, evaluates each by its similarity to the original question, and then selects the candidate solution with the highest similarity score as the final response. Since conventional SLMs struggle to generate accurate questions from their own reasoning paths and answers, we employ a lightweight Flan-T5 model specialized for question generation to support this process efficiently. From the experimental results, it is verified that CCQA consistently outperforms existing state-of-the-art (SOTA) methods across eight models on mathematical and commonsense reasoning benchmarks. Furthermore, our method establishes a new practical baseline for efficient reasoning in SLMs. Source code can be found at https://github.com/scai-research/ccqa_official.