# MeXtract: Light-Weight Metadata Extraction from Scientific Papers

arXiv: https://arxiv.org/abs/2510.06889 · HTML: https://mlsanity.com/paper/2510.06889/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 18 references that are in the map.
- First posted on arXiv 8 Oct 2025.

## Builds on (most cited first, 4 of 4)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation](https://mlsanity.com/paper/2403.06988/) (2024)
- [Learning to Generate Structured Output with Schema Reinforcement Learning](https://mlsanity.com/paper/2502.18878/) (2025)
- [Masader: Metadata Sourcing for Arabic Text and Speech Data Resources](https://mlsanity.com/paper/2110.06744/) (2021)

## Built on by (most cited first, 1 of 1)

- [CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets](https://mlsanity.com/paper/2610.07132/) (2026)

## Abstract (arXiv)

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.