Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generation
This work addresses the problem of dataset construction for specialized fields like science, where domain expertise is scarce, by providing a method to generate more comprehensive synthetic queries, though it is incremental as it builds on existing LLM-based approaches.
The paper tackles the challenge of incomplete concept coverage in synthetic query generation for scientific document retrieval by introducing the CCQGen framework, which adaptively generates queries to cover uncovered concepts, resulting in significant improvements in query quality and retrieval performance.
In specialized fields like the scientific domain, constructing large-scale human-annotated datasets poses a significant challenge due to the need for domain expertise. Recent methods have employed large language models to generate synthetic queries, which serve as proxies for actual user queries. However, they lack control over the content generated, often resulting in incomplete coverage of academic concepts in documents. We introduce Concept Coverage-based Query set Generation (CCQGen) framework, designed to generate a set of queries with comprehensive coverage of the document's concepts. A key distinction of CCQGen is that it adaptively adjusts the generation process based on the previously generated queries. We identify concepts not sufficiently covered by previous queries, and leverage them as conditions for subsequent query generation. This approach guides each new query to complement the previous ones, aiding in a thorough understanding of the document. Extensive experiments demonstrate that CCQGen significantly enhances query quality and retrieval performance.