GRS-QA -- Graph Reasoning-Structured Question Answering Dataset

TL;DR

GRS-QA is a new dataset that provides detailed reasoning structures for multi-hop question answering, enabling better evaluation of LLM reasoning abilities across different logical pathways.

Contribution

The paper introduces GRS-QA, a dataset with explicit reasoning graphs for QA pairs, allowing fine-grained analysis of LLM reasoning performance.

Findings

LLMs perform variably across different reasoning structures.

The dataset enables analysis of reasoning pathways versus semantic content.

Empirical results highlight the importance of reasoning structure in LLM performance.

Abstract

Large Language Models (LLMs) have excelled in multi-hop question-answering (M-QA) due to their advanced reasoning abilities. However, the impact of the inherent reasoning structures on LLM M-QA performance remains unclear, largely due to the absence of QA datasets that provide fine-grained reasoning structures. To address this gap, we introduce the Graph Reasoning-Structured Question Answering Dataset (GRS-QA), which includes both semantic contexts and reasoning structures for QA pairs. Unlike existing M-QA datasets, where different reasoning structures are entangled together, GRS-QA explicitly captures intricate reasoning pathways by constructing reasoning graphs, where nodes represent textual contexts and edges denote logical flows. These reasoning graphs of different structures enable a fine-grained evaluation of LLM reasoning capabilities across various reasoning structures. Our empirical analysis reveals that LLMs perform differently when handling questions with varying reasoning structures. This finding facilitates the exploration of textual structures as compared with semantics.