HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions
This provides a tool for the research community to automatically generate challenging benchmarks from any raw corpus, aiding evaluation and training of QA models, especially in resource-scarce domains.
The paper tackled the challenge of creating extensive and high-quality multi-hop question answering datasets by introducing HopWeaver, a cross-document framework that synthesizes authentic multi-hop questions without human intervention, achieving comparable or superior quality to human-annotated datasets at a lower cost.
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 QA models, especially in domains with scarce resources.