Metraipolis › archive › dc_ae77de6df747
Can Generative AI Automate Data Extraction for Meta-Analysis? A Case Study on Intercropping Research — arXiv:2609.35089
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35089
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:58:30.701Z
- SHA-256 of the archived text
2a79a0b60f630cc806ea4b5ba48d455fe2df260d04f13cf53e53e091cdea4432- Stable URL of this page
https://metraipolis.com/documento/dc_ae77de6df747
How to cite
Can Generative AI Automate Data Extraction for Meta-Analysis? A Case Study on Intercropping Research — arXiv:2609.35089 — arXiv (en), https://arxiv.org/abs/2609.35089 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae77de6df747 (Metraipolis archive dc_ae77de6df747, sha256 2a79a0b60f630cc806ea4b5ba48d455fe2df260d04f13cf53e53e091cdea4432)
BibTeX
@misc{dcae77de6df747,
title = {Can Generative AI Automate Data Extraction for Meta-Analysis? A Case Study on Intercropping Research — arXiv:2609.35089},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35089},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae77de6df747; sha256 2a79a0b60f630cc806ea4b5ba48d455fe2df260d04f13cf53e53e091cdea4432},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35089. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Meta-analysis is the synthesis of information from multiple sources to arrive at an overarching conclusion. There is a large need for meta-analysis in agricultural research to synthesize what is known and analyze overarching patterns. Extracting data from published literature is, however, labor-intensive, time-consuming, and tedious, and is impeded by a lack of standardization in research design, units of measurement, and terminology. These challenges are particularly evident in the domain of crop species mixtures, also called intercropping. With the growing capabilities of LLMs, many recent attempts have focused on building systems and tools to automate data collection, yet rigorous assessment against human-labeled ground truth is often missing. In this research, we evaluate three LLM-based approaches---direct zero-shot prompting, a staged workflow, and a multi-agent system---with six open-weight models to extract data from the intercropping literature. The results are evaluated against the manually curated ground truth and through a downstream statistical analysis. Overall, direct zero-shot prompting is the strongest and most consistent approach, achieving the highest mean similarity-adjusted F1 of 0.577, although none of the approaches is close to fully accurate. In the downstream analysis, most model--approach combinations recover the direction of the relationship between the predictor and outcome variables, but do not estimate its magnitude accurately. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.35089 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:01.773Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).