MeXtract: Light-Weight Metadata Extraction from Scientific Papers
This addresses the challenge of accurate and efficient metadata extraction for indexing and analyzing scientific literature, though it appears incremental as it builds on existing models and benchmarks.
The paper tackles the problem of extracting metadata from scientific papers by introducing MeXtract, a family of lightweight language models that achieve state-of-the-art performance on the MOLE benchmark, with models ranging from 0.5B to 3B parameters.
Metadata plays a critical role in indexing, documenting, and analyzing scientific literature, yet extracting it accurately and efficiently remains a challenging task. Traditional approaches often rely on rule-based or task-specific models, which struggle to generalize across domains and schema variations. In this paper, we present MeXtract, a family of lightweight language models designed for metadata extraction from scientific papers. The models, ranging from 0.5B to 3B parameters, are built by fine-tuning Qwen 2.5 counterparts. In their size family, MeXtract achieves state-of-the-art performance on metadata extraction on the MOLE benchmark. To further support evaluation, we extend the MOLE benchmark to incorporate model-specific metadata, providing an out-of-domain challenging subset. Our experiments show that fine-tuning on a given schema not only yields high accuracy but also transfers effectively to unseen schemas, demonstrating the robustness and adaptability of our approach. We release all the code, datasets, and models openly for the research community.