MétaCan
Menu
Back to cohort
Record W4414029501 · doi:10.1101/2025.08.31.672925

What Large Language Models Know About Plant Molecular Biology

2025· preprint· en· W4414029501 on OpenAlexaff
Manuel Fernandez Burda, Lucía Ferrero, Nicolás Gaggion, Camille Fonouni‐Farde, Martín Crespi, Federico Ariel, Enzo Ferrante, María Eugenia Zanetti, Anne Krapp, Regina Mencia, Facundo Romani, Jorge Muschietti, Natanael Mansilla, Jorge J. Casal, Luciana Anabella Pagnussat, Carlos L. Ballaré, María Florencia Mammarella, Flavio Antonio Blanco, Sonali Roy, Guillermo A. Maroniche, Máximo Rivarola, Diego F. Fiol, Pilar Cubas, Carlos A. Dezar, Paula Casati, Fernando Ibáñez, Fernanda de Carvalho‐Niebel, Dorothee Staiger, Corina M. Fusari, Gabriela Auge, María Verónica Arana, Rajni Parmar, Wenli Zhang, Saloni Mathur, Paul E. Verslues, Pablo A. Manavella, Julieta L. Mateos, Nicolas Bouché, Leandro Lucero, Marı́a F. Drincovich, Soledad Traubenik, Uciel Chorostecki, Gabriela Conti, Diego Zavallo, Elina Welchen, Florian Frugier, Rossana Henriques, Matthias Benoit, Carlos D. Crocco, Dong Wang, Peter Kindgren, Victoria Gastaldi, Ariel H. Tomassi, Julio Sáez‐Vasquez, Cristiane P. G. Calixto, Carlos M. Figueroa, Diana E. Gras, María Eugenia Segretin, Ezequiel Petrillo, Micaela A. Godoy Herz, Santiago Prochetto, Carolina Attallah, Gustavo Eduardo Gudesblat, Javier F. Palatnik, Martiniano M. Ricardi, Martina Legris, Selma Gago‐Zachert, Santiago Signorelli, Carlos García‐Mata, Cécile Raynaud, Sebastian Marquardt, Marcelo J. Yanovsky, Tomás María Tessi, Fernando Carrari, Pierre‐Marc Delaux, Tibor Csorba, José M. Estevez, Catharina Merchante, Wolfgang Busch, Alberto Carbonell, José M. Álvarez, Javier E. Moreno, Johan Rodríguez-Melo, Clara Bourbousse, V. V. Lia, Miguel Á. Blázquez, Pablo Ignacio Calzadilla, Sara Selma, Christian Fankhauser, Gabriela Soto, Thomas Blein, Ariel Orellana, Francisca Blanco‐Herrera, Nicolás E. Blanco, María Florencia Legascue, Carmen Martín‐Pizarro, David Posé, Moussa Benhamed, Briardo Llorente, Humberto Debat, Nicolás G. Bologna, Ana M. Laxalt, Rodrigo A. Gutiérrez, Andréas Niebel, Alexis Maizel, Pedro Crevillén, Ramiro E. Rodríguez, Laura Arribas‐Hernández, Chang Liu, Gabriela Carolina Pagnussat, Pablo D. Cerdán, Hervé Vaucheret

Bibliographic record

VenuebioRxiv (Cold Spring Harbor Laboratory) · 2025
Typepreprint
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsCanadian Nautical Research Society
FundersAgencia Nacional de Investigación y DesarrolloConsejo Nacional de Investigaciones Científicas y Técnicas
KeywordsComputational biologyBiologyComputer science

Abstract

fetched live from OpenAlex

ABSTRACT Large language models (LLMs) are rapidly permeating scientific research, yet their capabilities in plant molecular biology remain largely uncharacterized. Here, we present MOBIPLANT, the first comprehensive benchmark for evaluating LLMs in this domain, developed by a consortium of 112 plant scientists across 19 countries. MOBIPLANT comprises 565 expert-curated multiple-choice questions and 1,075 synthetically generated questions, spanning core topics from gene regulation to plant-environment interactions. We benchmarked seven leading chat-based LLMs using both automated scoring and human evaluation of open-ended answers. Models performed well on multiple-choice tasks (exceeding 75% accuracy), although most of them exhibited a consistent bias towards option A. In contrast, expert reviews exposed persistent limitations, including factual misalignment, hallucinations, and low self-awareness. Critically, we found that model performance strongly correlated with the citation frequency of source literature, suggesting that LLM knowledge inherits the visibility distribution of the underlying scientific corpus. Consequently, models tend to be more reliable on consolidated topics and less reliable on under-cited or recently emerging ones. We also benchmarked agents equipped with web-search and additional tools in more complex tasks involving DNA sequence analysis. These agents were outperformed by domain specific models in sequence classification and regression tasks, indicating an opportunity for joint agentic systems that combine both the reasoning power of LLMs and the dedicated processing of DNA models. This understanding is key to guiding both the development of next-generation models and the informed use of current tools in the everyday work of plant researchers. MOBIPLANT is publicly available online in this link .

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.856
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0030.003
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.013
GPT teacher head0.243
Teacher spread0.230 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venuebioRxiv (Cold Spring Harbor Laboratory)Same topicTopic ModelingFrench-language works237,207