Hybrid Graphs for Table-and-Text based Question Answering using LLMs

TL;DR

This paper introduces a novel hybrid graph approach for multi-source table-and-text question answering using large language models without fine-tuning, achieving state-of-the-art zero-shot performance and reducing token usage.

Contribution

It proposes a hybrid graph-based method that constructs a unified graph from text and tables, enabling effective reasoning over multi-source data with LLMs in a zero-shot setting.

Findings

Achieves up to 10% improvement in Exact Match scores on Hybrid-QA.

Reduces token usage by up to 53%.

Demonstrates effectiveness across GPT-3.5, GPT-4, and LLaMA-3.

Abstract

Answering questions that require reasoning and aggregation across both structured (tables) and unstructured (raw text) data sources presents significant challenges. Current methods rely on fine-tuning and high-quality, human-curated data, which is difficult to obtain. Recent advances in Large Language Models (LLMs) have shown promising results for multi-hop question answering (QA) over single-source text data in a zero-shot setting, yet exploration into multi-source Table-Text QA remains limited. In this paper, we present a novel Hybrid Graph-based approach for Table-Text QA that leverages LLMs without fine-tuning. Our method constructs a unified Hybrid Graph from textual and tabular data, pruning information based on the input question to provide the LLM with relevant context concisely. We evaluate our approach on the challenging Hybrid-QA and OTT-QA datasets using state-of-the-art LLMs, including GPT-3.5, GPT-4, and LLaMA-3. Our method achieves the best zero-shot performance on both datasets, improving Exact Match scores by up to 10% on Hybrid-QA and 5.4% on OTT-QA. Moreover, our approach reduces token usage by up to 53% compared to the original context.