HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions

TL;DR

HopWeaver is a novel cross-document framework that automatically synthesizes high-quality, authentic multi-hop questions for question answering systems, reducing manual effort and enabling scalable benchmark creation.

Contribution

It introduces a fully automated pipeline for generating realistic multi-hop questions without human intervention, advancing dataset creation for QA models.

Findings

Synthesized questions are comparable or superior to human-annotated datasets.

The framework reduces costs and manual effort in dataset creation.

Enables automatic generation of challenging benchmarks from raw corpora.

Abstract

Multi-Hop Question Answering (MHQA) is crucial for evaluating the model's capability to integrate information from diverse sources. However, creating extensive and high-quality MHQA datasets is challenging: (i) manual annotation is expensive, and (ii) current synthesis methods often produce simplistic questions or require extensive manual guidance. This paper introduces HopWeaver, the first cross-document framework synthesizing authentic multi-hop questions without human intervention. HopWeaver synthesizes bridge and comparison questions through an innovative pipeline that identifies complementary documents and constructs authentic reasoning paths to ensure true multi-hop reasoning. We further present a comprehensive system for evaluating the synthesized multi-hop questions. Empirical evaluations demonstrate that the synthesized questions achieve comparable or superior quality to human-annotated datasets at a lower cost. Our framework provides a valuable tool for the research community: it can automatically generate challenging benchmarks from any raw corpus, which opens new avenues for both evaluation and targeted training to improve the reasoning capabilities of advanced question answering models, especially in domains with scarce resources.