Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models

TL;DR

This paper introduces AoR, a hierarchical reasoning aggregation framework that improves answer selection in large language models by evaluating reasoning chains, especially in complex tasks, surpassing existing ensemble methods.

Contribution

The paper proposes AoR, a novel hierarchical reasoning aggregation framework that evaluates reasoning chains for better answer selection in LLMs, addressing limitations of answer frequency-based ensembling.

Findings

AoR outperforms prominent ensemble methods on complex reasoning tasks.

AoR adapts to various LLMs and achieves higher performance ceilings.

Dynamic sampling improves reasoning chain evaluation based on task complexity.

Abstract

Recent advancements in Chain-of-Thought prompting have facilitated significant breakthroughs for Large Language Models (LLMs) in complex reasoning tasks. Current research enhances the reasoning performance of LLMs by sampling multiple reasoning chains and ensembling based on the answer frequency. However, this approach fails in scenarios where the correct answers are in the minority. We identify this as a primary factor constraining the reasoning capabilities of LLMs, a limitation that cannot be resolved solely based on the predicted answers. To address this shortcoming, we introduce a hierarchical reasoning aggregation framework AoR (Aggregation of Reasoning), which selects answers based on the evaluation of reasoning chains. Additionally, AoR incorporates dynamic sampling, adjusting the number of reasoning chains in accordance with the complexity of the task. Experimental results on a series of complex reasoning tasks show that AoR outperforms prominent ensemble methods. Further analysis reveals that AoR not only adapts various LLMs but also achieves a superior performance ceiling when compared to current methods.