SEARCH · Engineering Papers

Results for “Large Language Models (LLMs)”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Trustworthiness and Trust: Identifying Factors that Drive Successful Human-AI Interaction in Nuclear Power Plant Applications

Emerging technologies such as artificial intelligence (AI) and machine learning (ML) are rapidly evolving and considered a promising tool for efficient and continued safe operations of the U.S. nuclear power plants (NPPs). Emerging AI techniques like large language models (LLMs) are one such technology that may support personnel at existing NPPs perform work more efficiently. For example, operators may query the current operational status of a power plant via a chat interface leveraging LLMs to access plant-related information in an interactive manner rather than manually collecting various sensor data for tasks such as surveillances or completing work orders. This is a fundamental shift in the way operators currently perform their tasks today. The literature of human-automation interaction indicates that trust is a crucial factor that drives successful interaction between a human operator and an automated system, like an AI-infused NPP application. This work presents the results of a literature review on key factors that relate to trust in AI/LLM technologies for NPP applications. The relevant literature of human factors and cognitive engineering has identified various factors related to trust including trustworthiness, performance characteristics, operator skill and perceived risk. This preliminary literature review will guide development and evaluation of models involving the identified factors influencing trust in AI and develop a framework for human-centered design for interface between humans and AI. By addressing trust, this work supports developing a technical basis for designing key characteristics of AI/LLM to support calibrated trust, which will ultimately support wide-scale adoption of AI/LLM technologies, as well as ensure safe, effective, and reliable use.

99 - GENERAL AND MISCELLANEOUS↗

NASA NTRSDate not supplied

LSKnowledge: Nexus for Transformative Scientific Discoveries and Enhanced Information Retrieval in NASA Life Sciences Portal

We stand at the brink of an extraordinary transformation in the field of AI, driven by the convergence of generative AI and semantic technologies (e.g., knowledge graphs). This fusion holds immense potential and could redefine the future of scientific exploration, particularly in the realm of life sciences research. In this context, we shed light on the pivotal roles that Large Language Models (LLMs) and semantic technologies will play in advancing research, unearthing and comprehending life sciences information through innovative approaches, and empowering researchers to extract insights from NASA's extensive Life Sciences Data Archive. Within the NASA Life Sciences Portal (NLSP), the integration of LLMs and semantic technologies unlocks several advanced capabilities. First and foremost, it equips scientists with sophisticated tools to manage the ever-expanding wealth of scientific literature and data. Furthermore, it facilitates the creation of knowledge graphs that visually represent intricate relationships among biological entities, enabling comprehensive systems-level analysis. Additionally, the fusion of generative AI (including LLMs) and semantic technology can significantly benefit NASA's life sciences research by enhancing information retrieval and hypothesis generation. These tools enhance natural language understanding, facilitating knowledge discovery within NLSP. The overarching vision is to establish a cohesive knowledge ecosystem within NLSP, harnessing the power of LLMs and semantic technologies to synthesize and cross-reference data from diverse missions, disciplines, and research domains. This holistic approach ultimately deepens our understanding of how space environments impact life sciences data. To advance this initiative, we have launched LSKnowledge, aimed at enhancing the information retrieval capabilities of NLSP. In the short term, our primary goal is to develop a robust semantic search system. This system will empower HRP (Human Research Program) researchers to navigate NLSP data repositories more efficiently and precisely, catalyzing the process of hypothesis formation and scientific breakthroughs. To achieve this, we have employed pre-trained LLMs as part of a semantic search tool that can rank and highlight the most relevant records for user queries. To assess the tool's performance, we have curated a set of approximately 200 queries from subject matter experts (SMEs) and manually ranked the top records retrieved by both the current search system and the new semantic search, using SME judgments as the gold standard for relevancy. Herein, we present the results of our comparative analysis and illustrate how these findings have informed the fine-tuning of the system for enhanced performance. In the long term, our objectives include 1) retrieving publicly available information and integrating it with NLSP data to provide more precise answers to user queries, and 2) incorporating non-textual information from the NLSP database into our approach. In conclusion, the fusion of LLMs and semantic technologies within NLSP represents a pioneering stride towards reshaping the landscape of scientific discovery. This synergy not only equips researchers with powerful tools to navigate the burgeoning sea of information but also facilitates a deeper understanding of complex biological relationships, all while accelerating hypothesis generation and knowledge discovery. Through our initiative, LSKnowledge, we are committed to continually refining and expanding these capabilities, with the aim of not only enhancing information retrieval but also integrating diverse data sources to provide more precise insights. In the grand vision, NLSP strives to become the cornerstone of a comprehensive knowledge ecosystem, unraveling the enigmatic intricacies of life sciences phenomena in the context of space environments.

Life Sciences↗

DOE OSTI2024

Dynamic Retrieval Augmented Generation of Ontologies using Artificial Intelligence (DRAGON-AI)

Ontologies are fundamental components of informatics infrastructure in domains such as biomedical, environmental, and food sciences, representing consensus knowledge in an accurate and computable form. However, their construction and maintenance demand substantial resources and necessitate substantial collaboration between domain experts, curators, and ontology experts. We present Dynamic Retrieval Augmented Generation of Ontologies using AI (DRAGON-AI), an ontology generation method employing Large Language Models (LLMs) and Retrieval Augmented Generation (RAG). DRAGON-AI can generate textual and logical ontology components, drawing from existing knowledge in multiple ontologies and unstructured text sources.We assessed performance of DRAGON-AI on de novo term construction across ten diverse ontologies, making use of extensive manual evaluation of results. Our method has high precision for relationship generation, but has slightly lower precision than from logic-based reasoning. Our method is also able to generate definitions deemed acceptable by expert evaluators, but these scored worse than human-authored definitions. Notably, evaluators with the highest level of confidence in a domain were better able to discern flaws in AI-generated definitions. We also demonstrated the ability of DRAGON-AI to incorporate natural language instructions in the form of GitHub issues.These findings suggest DRAGON-AI's potential to substantially aid the manual ontology construction process. However, our results also underscore the importance of having expert curators and ontology editors drive the ontology generation process.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2023

Evaluation of pre-training large language models on leadership-class supercomputers

Large language models (LLMs) have arisen rapidly to the center stage of artificial intelligence as the foundation models applicable to many downstream learning tasks. However, how to effectively build, train, and serve such models for many high-stake and first-principle-based scientific use cases are both of great interests and of great challenges. Moreover, pre-training LLMs with billions or even trillions of parameters can be prohibitively expensive not just for academic institutions, but also for well-funded industrial and government labs. Furthermore, the energy cost and the environmental impact of developing LLMs must be kept in mind. Here, in this work, we conduct a first-of-its-kind performance analysis to understand the time and energy cost of pre-training LLMs on the Department of Energy (DOE)’s leadership-class supercomputers. Employing state-of-the-art distributed training techniques, we evaluate the computational performance of various parallelization approaches at scale for a range of model sizes, and establish a projection model for the cost of full training. Our findings provide baseline results, best practices, and heuristics for pre-training such large models that should be valuable to HPC community at large. We also offer insights and optimization strategies for using the first exascale computing system, Frontier, to train models of the size of GPT-3 and beyond.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Leveraging large language models to address data scarcity in machine learning for graphene synthesis

Machine learning in experimental materials science faces significant challenges due to the scarcity of data, which are costly and time-consuming to generate, particularly when relying on in-house experiments. Literature data mining offers a potential solution but introduces issues like mixed data quality, inconsistent formats, and non-uniform reporting of synthesis parameters, resulting in partially missing and heterogeneous features across the dataset. Here, we propose data imputation and feature engineering methods that employ pre-trained large language models (LLMs) to enhance machine learning performance on scarce, heterogeneous datasets, demonstrated on graphene CVD synthesis data and the ML-HydPARK hydrogen storage dataset. GPT models perform data imputation via tailored prompting and semantic normalization of inconsistently reported features through embeddings, for example, to harmonize the complex nomenclature of CVD substrates. Beyond yielding more diverse and richer feature representations than traditional methods such as K-nearest neighbors (KNN) and Multivariate Imputation by Chained Equations (MICE), LLM-based data imputation is evaluated against dataset characteristics and prompting strategies. We vary the level of autonomy granted to the LLM, from generic prompting that leverages pre-trained knowledge for autonomous data generation to data-informed prompting that constrains outputs using target-specific information, and demonstrate which level of autonomy yields superior imputation performance across datasets and feature types. The proposed data engineering methods markedly improve downstream performance; for example, in graphene layer number classification using a support vector machine (SVM), binary accuracy increases from 39% to 65% and ternary accuracy from 52% to 72%. Fine-tuning experiments on both datasets show that combining our proposed LLM-based data imputation and feature encoding methods with numerical machine learning predictors outperforms standalone fine-tuned LLM predictors in data-scarce settings. The proposed strategies emphasize data enhancement techniques rather than refining learning architectures or regularizing loss functions, offering a broadly applicable framework for improving machine learning performance on scarce, inhomogeneous datasets.

Chemical vapor deposition↗

DOE OSTI2024

Powering Data Centers with Clean Energy: A Techno-Economic Case Study of Nuclear and Renewable Energy Dependability

Rising data demands from artificial intelligence (AI) and large language models (LLMs) generating images, videos, and text have prompted increased need for larger and more robust data centers in the United States. Major companies interested in these larger data centers face the choice of linking them to existing regional grids, building stand-alone power supplies onsite, or a combination of both. The request, review, and approval process for new transmission lines to grids in the United States, however, has grown in recent years to times spans rivaling those of new construction for nuclear power plants. Building an islanded power supply for each data center is therefore becoming a prominent option. In this case study, several technologies are modeled in techno-economic simulations for long-term system costs subject to fixed electricity demand from a singular data center. A 250 MWe data center is assumed with additional 50 MWe for resiliency. Techno-economic simulations are conducted using the Holistic Energy Resource Optimization Network (HERON) software, which is a part of the Framework for Optimization of Resources and Economics (FORCE) tool suite. Technologies considered include solar, wind, lithium-ion batteries, and several types of nuclear reactors: large-scale reactors, small modular reactors, and microreactors. A low- and high-cost estimate for each technology is assumed to develop a range of expected economic performance. Low-cost estimates included several clean energy production tax credits. Different combinations of renewable energy generators with nuclear reactors are considered, ranging from a fully renewable-powered data center to a fully nuclear-powered data center. Historic time series of wind and solar availability from the Texas grid are used to train a reduced order model; this model then generates unique time series with similar characteristics of the training dataset. Multiple scenarios of weather and subsequent operations are simulated for each renewable-nuclear combination to determine total costs throughout the project lifetime. Fully renewable-powered configurations required large amounts of installed capacity (GW scale) in the simulations to meet the fixed demand of the data center. This is due to some scenarios in the historical dataset which captured low-wind and low-solar days, requiring over-building of these technologies as well as batteries to compensate for the low amounts of electricity generation. Fully nuclear-powered configurations outperformed the fully renewable and mixed renewable-nuclear configurations in terms of cost, with ranges between $1B and $10B in 2023 USDs compared to $40B+ for fully renewable configurations. Of the nuclear technologies, small modular reactors performed better economically than large-scale nuclear models due to lower projected capital costs, and both performed better than the microreactor models. These results demonstrate the applicability of firm, dispatchable electricity resources from baseload generators like nuclear power plants for operating facilities that run at constant power without daily variability.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2024

Towards Next-Generation Urban Decision Support Systems through AI-Powered Construction of Scientific Ontology Using Large Language Models—A Case in Optimizing Intermodal Freight Transportation

The incorporation of Artificial Intelligence (AI) models into various optimization systems is on the rise. However, addressing complex urban and environmental management challenges often demands deep expertise in domain science and informatics. This expertise is essential for deriving data and simulation-driven insights that support informed decision-making. In this context, we investigate the potential of leveraging the pre-trained Large Language Models (LLMs) to create knowledge representations for supporting operations research. By adopting ChatGPT-4 API as the reasoning core, we outline an applied workflow that encompasses natural language processing, Methontology-based prompt tuning, and Generative Pre-trained Transformer (GPT), to automate the construction of scenario-based ontologies using existing research articles and technical manuals of urban datasets and simulations. From these ontologies, knowledge graphs can be derived using widely adopted formats and protocols, guiding various tasks towards data-informed decision support. The performance of our methodology is evaluated through a comparative analysis that contrasts our AI-generated ontology with the widely recognized pizza ontology, commonly used in tutorials for popular ontology software. We conclude with a real-world case study on optimizing the complex system of multi-modal freight transportation. Our approach advances urban decision support systems by enhancing data and metadata modeling, improving data integration and simulation coupling, and guiding the development of decision support strategies and essential software components.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2025

LLM Benchmarking with LLaMA2: Evaluating Code Development Performance Across Multiple Programming Languages

The rapid evolution of large language models (LLMs) has opened new possibilities for automating various tasks in software development. This paper evaluates the capabilities of the LLaMA 2-70B model in automating these tasks for scientific applications written in commonly used programming languages. Using representative test problems, we assess the model's capacity to generate code, documentation, and unit tests, as well as its ability to translate existing code between commonly used programming languages. Our comprehensive analysis evaluates the compilation, runtime behavior, and correctness of the generated and translated code. Additionally, we assess the quality of automatically generated code, documentation, and unit tests. Here, our results indicate that while LLaMA 2-70B frequently generates syntactically correct and functional code for simpler numerical tasks, it encounters substantial difficulties with more complex, parallelized, or distributed computations, requiring considerable manual corrections. We identify key limitations and suggest areas for future improvements to better leverage AI-driven automation in scientific computing workflows.

97 MATHEMATICS AND COMPUTING↗

NASA NTRSDate not supplied

Developing Concepts of Operations Using Multi-Step Tool Techniques With Large Language Models

The National Aeronautics and Space Administration (NASA) Air Mobility Pathfinders (AMP) project is developing and evaluating concepts of operations (ConOps) for safe, secure, and scalable Urban Air Mobility (UAM) operations. The AMP project’s Operational Concepts, Architecture, and Requirements Integration (OCARI) Team is using a Model Based System Engineering (MBSE) approach for integration, interoperability, and traceability of Advanced Air Mobility (AAM) ecosystems centered around urban air taxi services. The team’s goal is to define structures and behaviors needed for system feasibility, readiness, and interoperability, establish a UAM knowledge base, and trace and validate assumptions and requirements relevant to AAM. NASA Langley Research Center (LaRC) is spearheading an innovative digital engineering approach to integrate, communicate, and facilitate the research of multi-modal transportation systems. The Knowledge-based Digital Platform (KbDP) is a concept being developed that ties the workflows of Project Managers (PM), Principal Investigators (PI), and System Engineers together across organizational boundaries. It does so through the management of an information database defined by mathematical, data science, and system engineering principles. Machine Learning (ML) algorithms play a key role in this concept by extracting meaningful knowledge from relational and graph databases, document repositories, and system artifacts, which the human user leverages to greatly improve the efficiency and effectiveness of their research. Recent advancements in the field of Large Language Models (LLMs), specifically models trained for tool use, such as Command-R , now allow for the reliable implementation of single-step and multi-step tool-centric systems. These techniques provide the LLM with a set of tools, in our case Python functions, that can be called on to answer a much wider range of questions compared to LLMs implemented using a traditional single-source or Retrieval Augmented Generation (RAG) approach. Through this method, the LLM can pull information from multiple data sources, such as relational or graph databases, document repositories, application programming interfaces (APIs), and SysML artifacts depending on the user’s question. The LLM can also output the information in a variety of different formats, using output generation tools, such as CSV, UML, or SysML artifacts. Additionally, tools can be assigned roles and can work together to provide answers to queries in an “agent” like approach, similar to that implemented by Microsoft’s AutoGen framework where different agents can converse with each other to accomplish tasks. Previously, our team developed a chatbot system with “agent like” functionality in the form of different “modes” the user could select from a user interface (UI), this architecture can be seen on the left in figure 1. Three different modes were implemented, the first mode allowed the LLM to utilize the structures and algorithms within a graph database to trace UAM requirements. The second mode gave the LLM access to a vector search capable of providing relevant information from thousands of document pages related to UAM ConOps and requirements. The third mode served as a general assistant where users could enter open-ended questions and custom prompts to utilize the LLM for different use-cases. This system improved the process surrounding generating and analyzing information related to UAM requirements, however, the implementation provided a clunky user experience. Users were required to know what mode to select within the UI in advance before entering their question to the selected tool. Moreover, the different tools were isolated from each other, they lacked bidirectional links that would allow for tools to collaborate to generate better responses. Our team is working on a new architecture, seen on the right in the below figure, with the goal to address many of the UX shortcomings of our original system while improving the accuracy and depth of responses from the LLM. This new system will automatically select the appropriate tool to use based off the user’s question. Each tool will be capable of calling on any of the other tools available to the LLM, resulting in a collaborative pipeline where tools can pass data between other tools until enough data is received to generate an answer to the user’s question. Using a locally deployed, open-source, LLM, the NASA OCARI team, in collaboration with Collins Aerospace, will implement a prototype application that will bridge knowledge across multiple sources to assist System Engineers (SEs) with requirements discovery and tracing, research question and use case identification, and assumption validation. Such a system will also allow SEs to more easily, and intuitively, explore the AAM ecosystem, ultimately improving the efficiency and effectiveness of the SE's research and decision-making processes surrounding ConOps development and validation. In this session, our team will provide a video demonstration of our new prototype architecture in action. We will also present an overview of our prototype system architecture and talk about its advantages over traditional LLM deployments along with how those advantages can provide additional value to the field of System Engineering.

systems engineering↗

DOE OSTI2026

Agentic framework for programmatic crystal structure generation using a fine-tuned worker–supervisor large language model

Platinum group metals (PGMs) underpin many catalytic technologies but face severe supply constraints, motivating the search for alternative materials and computational methods to accelerate discovery. While atomistic simulation tools such as Pymatgen and ASE have streamlined structure manipulation, they require detailed inputs, limiting accessibility for experimentalists and slowing early-stage exploration. Here, in this study, we present an AI-driven agentic framework that orchestrates worker–supervisor large language models (LLMs). The worker translates natural-language prompts of varying abstraction into valid crystallographic structures using a compact LLM fine-tuned with low-rank adaptation on a curated text–code–CIF dataset, emphasizing energy-efficient training. Benchmarking against the baseline CodeGen-350M-mono model shows that fine-tuning reduces hallucination rates from 100% to as low as 5% and improves structural match accuracy to up to 82% for fully specified inputs. Accuracy declines with decreasing prompt detail but remains nontrivial even when only stoichiometry and space group are provided, underscoring the LLM’s capacity for crystallographic inference. The supervisor Claude LLM evaluates the outputs and triggers iterative refinement through the worker’s built-in structure manipulation capabilities (e.g., supercell scaling, strain, vacancy, and substitution operations). We further demonstrate use cases for technologically relevant catalysts, including IrO 2 , pyrochlore Pb 2 Ir 2 O 7 , Ni 2 FeO 4 , and Ni 3 Mo, where the framework generates physically consistent structures that can be refined via geometry optimization. This work introduces a low-energy, language-driven pathway for integrating human and machine intelligence in materials design, paving the way for AI-assisted synthesis planning and high-throughput screening of complex oxides.

AI agent↗

DOE OSTI2025

Explainable Synthesizability Prediction of Inorganic Crystal Polymorphs Using Large Language Models

Abstract We evaluate the ability of machine learning to predict whether a hypothetical crystal structure can be synthesized and explain those predictions to scientists. Fine‐tuned large language models (LLMs) trained on a human‐readable text description of the target crystal structure perform comparably to previous bespoke convolutional graph neural network methods, but better prediction quality can be achieved by training a positive‐unlabeled learning model on a text‐embedding representation of the structure. An LLM‐based workflow can then be used to generate human‐readable explanations for the types of factors governing synthesizability, extract the underlying physical rules, and assess the veracity of those rules. These explanations can guide chemists in modifying or optimizing non‐synthesizable hypothetical structures to make them more feasible for materials design.

Kim, Seongmin [Department of Chemical and Biologic↗

DOE OSTI2025

Explainable Synthesizability Prediction of Inorganic Crystal Polymorphs Using Large Language Models

Kim, Seongmin [Department of Chemical and Biologic↗

DOE OSTI2024

chatHPC: Empowering HPC users with large language models

The ever-growing number of pre-trained large language models (LLMs) across scientific domains presents a challenge for application developers. While these models offer vast potential, fine-tuning them with custom data, aligning them for specific tasks, and evaluating their performance remain crucial steps for effective utilization. However, applying these techniques to models with tens of billions of parameters can take days or even weeks on modern workstations, making the cumulative cost of model comparison and evaluation a significant barrier to LLM-based application development. To address this challenge, we introduce an end-to-end pipeline specifically designed for building conversational and programmable AI agents on high performance computing (HPC) platforms. Our comprehensive pipeline encompasses: model pre-training, fine-tuning, web and API service deployment, along with crucial evaluations for lexical coherence, semantic accuracy, hallucination detection, and privacy considerations. Here, we demonstrate our pipeline through the development of chatHPC, a chatbot for HPC question answering and script generation. Leveraging our scalable pipeline, we achieve end-to-end LLM alignment in under an hour on the Frontier supercomputer. We propose a novel self-improved, self-instruction method for instruction set generation, investigate scaling and fine-tuning strategies, and conduct a systematic evaluation of model performance. The established practices within chatHPC will serve as a valuable guidance for future LLM-based application development on HPC platforms.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Text Mining for Process–Structure–Properties Relationships in Metals

With the advent of large language models (LLMs), the vast unstructured text within millions of academic papers is increasingly accessible for materials discovery—although significant challenges remain. While LLMs offer promising few- and zero-shot learning capabilities, particularly valuable in the materials domain where expert annotations are scarce, general-purpose LLMs often fail to address key materials-specific queries without further adaptation. To bridge this gap, fine-tuning LLMs on human-labeled data is essential for effective structured knowledge extraction (Liu in The Importance of Human-Labeled Data in the Era of LLMs, 2023). Here, in this study, we introduce a novel annotation schema designed to extract generic process–structure–properties relationships from scientific literature. We demonstrate the utility of this approach using a dataset of 128 abstracts, with annotations drawn from two distinct domains: high-temperature materials (Domain I) and uncertainty quantification in simulating materials microstructure (Domain II). Initially, we developed a conditional random field (CRF) model based on MatBERT—a domain-specific BERT variant—and evaluated its performance on Domain I. Subsequently, we compared this model with a fine-tuned LLM (GPT-4o from OpenAI) under identical conditions. Our results indicate that fine-tuning LLMs can significantly improve entity extraction performance over the BERT-CRF baseline on Domain I. However, when additional examples from Domain II were incorporated, the performance of the BERT-CRF model became comparable to that of the GPT-4o model. These findings underscore the potential of our schema for structured knowledge extraction and highlight the complementary strengths of both modeling approaches.

Materials science↗

DOE OSTI2025

Language models for materials discovery and sustainability: Progress, challenges, and opportunities

Significant advancements have been made in one of the most critical branches of artificial intelligence: natural language processing (NLP). These advancements are exemplified by the remarkable success of OpenAI’s GPT-3.5/4 and the recent release of GPT-4.5, which have sparked a global surge of interest akin to an NLP gold rush. Here, in this article, we offer our perspective on the development and application of NLP and large language models (LLMs) in materials science. We begin by presenting an overview of recent advancements in NLP within the broader scientific landscape, with a particular focus on their relevance to materials science. Next, we examine how NLP can facilitate the understanding and design of novel materials and its potential integration with other methodologies. To highlight key challenges and opportunities, we delve into three specific topics: (i) the limitations of LLMs and their implications for materials science applications, (ii) the creation of a fully automated materials discovery pipeline, and (iii) the potential of GPT-like tools to synthesize existing knowledge and aid in the design of sustainable materials.

36 MATERIALS SCIENCE↗

DOE OSTI2025

MechBERT: Language Models for Extracting Chemical and Property Relationships about Mechanical Stress and Strain

Language models are transforming materials-aware naturallanguage processing by enabling the extraction of dynamic, context-rich information from unstructured text, thus, moving beyond the limitations of traditional information-extraction methods. Moreover, small language models are on the rise because some of them can perform better than large language models (LLMs) when given domain-specific questionanswer tasks, especially about an application area that relies on a highly specialized vernacular, such as materials science. We therefore present a new class of MechBERT language models for understanding mechanical stress and strain in materials. These employ Bidirectional Encoder Representations for transformer (BERT) architectures. We showcase four MechBERT models, all of which were pretrained on a corpus of documents that are textually rich in chemicals and their stress–strain properties and were fine-tuned on question-answering tasks. We evaluated the level of performance of our models on domain-specific as well as general English-language question-answer tasks and also explored the influence of the size and type of BERT architectures on model performance. We find that our MechBERT models outperform BERT-based models of the same size and maintain relevancy better than much larger BERT-based models when tasked with domain-specific question-answering tasks within the stress–strain engineering sector. These small language models also enable much faster processing and require a much smaller fraction of data to pretrain them, affording them greater operational efficiency and energy sustainability than LLMs.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2026

Leveraging Large Language Models for Understanding Fundamental Principles of Catalysis

Heterogeneous catalysis presents a distinct challenge for artificial intelligence (AI). Data sets are often small and inconsistently reported, catalyst representations are not standardized, and extracting fundamental knowledge requires integrating performance data, spectroscopic characterizations, and mechanistic models across multiple scales. Language offers a unifying representation across these modalities, making catalysis well suited for leveraging large language models (LLMs). By standardizing how catalytic data is represented, LLMs make dispersed experimental results more accessible to downstream statistical modeling. In this perspective, we focus our discussion around three opportunities where LLMs can significantly contribute to catalysis: (1) text to properties; (2) text to structure; and (3) text to mechanistic models. The discussion is followed by a perspective section on LLM-readiness of data, aligning LLM outputs with scientific correctness, and bridging lab-scale discovery to industrial deployment. Across each area, the most productive applications couple dispersed chemical knowledge with physics-grounded validation to produce verifiable hypotheses and actionable representations.

Catalysts↗

DOE OSTI2026

Bayesian Optimization of Catalysis with In-Context Learning

Large language models (LLMs) can perform accurate classification with zero or few examples through in-context learning (ICL), allowing the model to observe query-relevant examples at inference time and eliminating the need for additional weight updates to generalize beyond its original training data. We extend this capability to regression with uncertainty estimation using frozen LLMs (e.g., GPT-4o, Gemini), enabling Bayesian optimization (BO) in natural language without explicit model training or feature engineering. We apply this to materials discovery by representing materials as synthesis and testing procedures for use in natural language prompts. This Bayesian, design-first approach prioritizes optimization toward target material properties before detailed characterization, in contrast to conventional experimental workflows that often emphasize characterization of suboptimal materials. On benchmarks like aqueous solubility and oxidative coupling of methane (OCM), BO-ICL matches or outperforms Gaussian processes. In live experiments on the reverse water–gas shift (RWGS) reaction, BO-ICL identifies multimetallic catalysts that approach equilibrium CO yield within 6 and 10 iterations from a pool of 3,700 and 360,000 candidates, respectively. Our method redefines materials representation and accelerates discovery, with broad applications across catalysis, materials science, and AI.

Calibration↗