Fostering Scientific Judgment in LLM-Assisted Catalyst Development

Abstract Large language models (LLMs) can provide plausible synthesis methods and reaction conditions for catalysis experiments in response to simple prompts, but the validity and accuracy of the responses are not necessarily reliable. We evaluated a zero-shot GPT-5 proposal for a trimetallic, precious metal-free reverse water–gas shift catalyst. The output initially appeared chemically plausible, but we identified errors by tasking students to verify the model’s claims against the primary literature, thermodynamic constraints, and control experiments. We then fed our observations and experimental results back into the model with a second prompt to determine whether the model would converge on a more scientifically grounded and experimentally testable catalyst candidate. Although the revised catalyst did not improve performance, the process revealed unexpected findings about catalyst stability and generated new hypotheses. Ultimately, our results show that iterative model verification can transform plausible but unreliable LLM outputs into a useful framework for student-driven catalyst preparation, hypothesis generation, and scientific training.

Authors

Institutions

Publication Details

Journal
ACS Applied Catalysis
Published
2026-11-13
DOI
https://doi.org/10.1021/acsappcat.6c00162
Primary Topic
Machine Learning in Materials Science
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Fostering Scientific Judgment in LLM-Assisted Catalyst Development

Devansh Pathak, Sinhara M. H. D. Perera, Marc D. Porosoff, Fawzia Islam Era et al.
4 links
ACS Applied Catalysis
Machine Learning in Materials Science
article

Fostering Scientific Judgment in LLM-Assisted Catalyst Development

Devansh Pathak, Sinhara M. H. D. Perera, Marc D. Porosoff, Fawzia Islam Era, Matthew Moran
article en

Abstract

Abstract Large language models (LLMs) can provide plausible synthesis methods and reaction conditions for catalysis experiments in response to simple prompts, but the validity and accuracy of the responses are not necessarily reliable. We evaluated a zero-shot GPT-5 proposal for a trimetallic, precious metal-free reverse water–gas shift catalyst. The output initially appeared chemically plausible, but we identified errors by tasking students to verify the model’s claims against the primary literature, thermodynamic constraints, and control experiments. We then fed our observations and experimental results back into the model with a second prompt to determine whether the model would converge on a more scientifically grounded and experimentally testable catalyst candidate. Although the revised catalyst did not improve performance, the process revealed unexpected findings about catalyst stability and generated new hypotheses. Ultimately, our results show that iterative model verification can transform plausible but unreliable LLM outputs into a useful framework for student-driven catalyst preparation, hypothesis generation, and scientific training.

ACS Applied Catalysis
University of Rochester (US)
National Science Foundation, U.S. Department of Energy, Division of Chemical, Bioengineering, Environmental, and Transport Systems, Basic Energy Sciences
Machine Learning in Materials Science
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon