What question did this study set out to answer?

This research aims to utilize large language models to extract structured data related to the medicinal uses of plants and fungi from scientific literature.

July 26, 2026Plants People PlanetOpen Access

Large language models unlock large text corpora in the search for data on medicinal plants and fungi

View Full Paper

Ask AI

Bookmark

Authors

ARAdam Richard‐Bollans FCFrancesco Civita TCTiziana Antonella Cossu

Discussion

Member takes

Overview

Randomized trial explores automated extraction of medicinal data using large language models, highlighting its potential benefits.

Key Points

This research aims to utilize large language models to extract structured data related to the medicinal uses of plants and fungi from scientific literature.
Developed a pipeline to mine data from the CORE dataset of open-access papers.
Annotated an initial subset of 10 papers for scientific names and medicinal effects.
Evaluated the performance of several large language models, including GPT 4o, on the extraction task.
GPT 4o achieved an F1 score of 0.63 for extracting scientific name-medical condition/medicinal effect relations.
After fine-tuning, GPT 4o achieved a precision of 0.85, identifying 284 scientific name-medical condition pairs and 363 scientific name-medicinal effect pairs.
The study demonstrated the effective use of LLMs to enhance the ethnopharmacological database and support traditional medicine research.

Cite This Study

Richard‐Bollans et al. (2026) studied this question.

synapsesocial.com/papers/6a65a422d3aea3239cd76dd2 https://doi.org/10.1002/ppp3.70250

View Full Paper

Ask AI

Bookmark

July 26, 2026Plants People PlanetOpen Access

Large language models unlock large text corpora in the search for data on medicinal plants and fungi

View Full Paper

Ask AI

Bookmark

Authors

ARAdam Richard‐Bollans FCFrancesco Civita TCTiziana Antonella Cossu

Discussion

Member takes

Overview

Randomized trial explores automated extraction of medicinal data using large language models, highlighting its potential benefits.

Key Points

This research aims to utilize large language models to extract structured data related to the medicinal uses of plants and fungi from scientific literature.
Developed a pipeline to mine data from the CORE dataset of open-access papers.
Annotated an initial subset of 10 papers for scientific names and medicinal effects.
Evaluated the performance of several large language models, including GPT 4o, on the extraction task.
GPT 4o achieved an F1 score of 0.63 for extracting scientific name-medical condition/medicinal effect relations.
After fine-tuning, GPT 4o achieved a precision of 0.85, identifying 284 scientific name-medical condition pairs and 363 scientific name-medicinal effect pairs.
The study demonstrated the effective use of LLMs to enhance the ethnopharmacological database and support traditional medicine research.

Cite This Study

Richard‐Bollans et al. (2026) studied this question.

synapsesocial.com/papers/6a65a422d3aea3239cd76dd2 https://doi.org/10.1002/ppp3.70250

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark