SEARCH · Engineering Papers

Results for “LLM performance”

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 73 records · Page 4

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Extraction and Analysis of Time Series Data from Building Automation Systems Using Large Language Models

Semantic schemas like Haystack 4, Brick and ASHRAE standard 223 enable the structured, standardized, and machine-readable representation of building data, facilitating interoperability, data integration, and advanced analytics. However, extracting information from these models requires specialized expertise in SPARQL and other programming languages, skills that are not commonly found among building professionals. Recent advancements in Large Language Models (LLMs), such as ChatGPT, enable the construction of queries using natural language, making it easier for individuals to interact with these systems in a manner that resembles everyday speech. However, these methods have not yet been tested on building semantic ontologies. This paper introduces a novel workflow and tool for enabling users to ask questions about a specific building's data, using natural language and receive answers automatically generated by GPT-4o. Our approach integrates semantic ontologies with advanced LLM capabilities to automate three critical steps: (1) generating SPARQL queries to retrieve time series references from ontological models, (2) extracting the corresponding time series data from the Building Automation System, and (3) performing computations and visualizations tailored to the user's query. The proposed method simplifies access to BAS data, allowing both domain experts and non-specialists to conduct sophisticated analyses without needing extensive technical knowledge of semantic web technologies. By demonstrating this pipeline, we facilitate more accessible and scalable data-driven decision-making in building operations and management.

Mulayim, Ozan Baris↗

DOE OSTI2025

Extraction and Analysis of Time Series Data from Building Automation Systems Using Large Language Models

Mulayim, Ozan Baris↗

NASA NTRSDate not supplied

LLMs and GenAI Tools to Depict Contributions of Human Systems to Spaceflight Tasks Execution

Recent advancements in Artificial Intelligence and Machine Learning (AI/ML) technologies, particularly Large Language Models (LLMs) capable of sophisticated syntax analysis, offer substantial potential in automating complex processes, thereby saving time and human resources. This study explores the development of an LLM-driven model designed to analyze and categorize a diverse set of Mars mission tasks into 18 predefined Human System Task Categories (HSTCs) based on their textual descriptions. As part of developing the Crew Health and Performance – Probabilistic Risk Assessment (CHP-PRA projects Performance Risk Model (PRisM) proof-of-concept, we established a framework to project performance scores from small-scale tests onto a preliminary list of Mars tasks. The foundation of our model was a comprehensive spreadsheet populated by NASA experts and clinicians, which detailed each Mars task alongside binary indicators of HSTC involvement. This dataset enabled the initial application of supervised ML, training and testing on existing HSTC labels. The HSTCs were originally defined from a medical system perspective, focusing on task impairments due to deteriorated human health. To expand our model's scope to include categories impacting performance, we face the challenge of generating binary labels (0 or 1) for new categories without pre-existing data. We address this by employing Generative AI (GenAI) software to determine whether a given task involved a new category by asking, "Does task A involve using category B?" We validate our approach by comparing the GenAI's binary classifications with the expert-provided labels for existing HSTCs. Notably, we utilize Ollama [4], a locally hosted GenAI tool that does not require cloud access, thus safeguarding NASA's proprietary data from unauthorized exposure. This study demonstrates the feasibility of leveraging cutting-edge AI tools to advance research, paving the way for automation and rapid decision-making in space exploration.

Mona Matar↗

NASA NTRS2008

16 Weeks of Training with the International Space Station Advanced Resistive Exercise Device (aRED) Is not Different than Training with Free Weights

The advanced Resistive Exercise Device (aRED) is a resistive exercise system designed to maintain muscle mass and strength in microgravity by simulating free weight (FW) exercise. aRED utilizes vacuum cylinders and inertial flywheels to replicate the constant mass and inertial components, respectively, of FW exercise in normal gravity. PURPOSE: To compare the effectiveness of aRED and FW resistive exercise training in ambulatory subjects. METHODS: Untrained subjects were assigned to two groups, FW (6 males, 3 females) and aRED (8 males, 3 females), and performed squat (SQ), heel raise (HR), and deadlift (DL) exercises 3 d wk-1 for 16 wks. SQ, HR and DL strength (1RM) were measured using FW hardware pre-, mid- and post-training. Subjects participated in a periodized training protocol with the exercise prescription based on a percentage of 1RM. Thigh and lower leg muscle volume were assessed using Magnetic Resonance Imaging (MRI), and leg (LLM) and total body lean mass (BLM) were measured using Dual Energy X-ray Absorptiometry (DXA) pre- and post-training. RESULTS: SQ 1RM increased in both FW (48.9+/-6.1%) and aRED (31.2+/-3.8%) groups, and there was a greater training response in FW compared with aRED (p=0.01). HR and DL 1RM increased in FW (HR: 12.3+/-2.4%, DL: 23.3+/-4.4%) and aRED (HR: 18.0+/-1.6%, DL: 23.2+'-2.8%), but there were no differences between groups. Thigh muscle volume was greater following training in both groups (FW: 9.8+/-0.9%, aRED: 7.1+/-1.2%) but lower leg muscle volume increased only in the FW group (3.0+/-1.1%). Lean tissue mass increased in both FW (LLM: 3.9+/-1.1%, BLM: 2.5+/-0.7%) and aRED (LLM: 4.8+/-0.7%, BLM: 2.6 0.7%). There were no between group differences in muscle volume or lean mass in response to training. CONCLUSIONS: In general, the increase in muscle strength, muscle volume, and lean tissue mass when training with aRED was not different than when using the same training protocol with FW. The smaller increase in SQ 1RM in the aRED group may be the result of undersizing the aRED flywheels which were intended to mimic the inertial component of the SQ movement when performing FW exercises. However, the biomechanical differences observed in body position during the performance of the aRED SQ, which may have affected training and testing, cannot be excluded as a factor that may have affected SQ 1RM results. PRACTICAL APPLICATIONS: Improvements in muscle strength, muscle volume and lean mass similar to FW exercise training may be elicited using an alternative source of resistance during exercise training. The acceleration of a mass during resistive exercise may result in greater muscle tension when changing the direction of movement resulting in enhanced strength gains. Therefore, to maximize the benefits of resistive exercise, the inertial components of FW exercise should be considered during exercise selection and hardware design. ACKNOWLEDGEMENT: This investigation was supported by NASA-JSC s Exercise Countermeasures Project.

Loehr, J. A.↗

DOE OSTI2025

Scaling Laws of Graph Neural Networks for Atomistic Materials Modeling

Atomistic materials modeling is a critical task with wide-ranging applications, from drug discovery to materials science, where accurate predictions of the target material property can lead to significant advancements in scientific discovery. Graph Neural Networks (GNNs) represent the state-of-the-art approach for modeling atomistic material data thanks to their capacity to capture complex relational structures. While machine learning performance has historically improved with larger models and datasets, GNNs for atomistic materials modeling remain relatively small compared to large language models (LLMs), which leverage billions of parameters and terabyte-scale datasets to achieve remarkable performance in their respective domains. To address this gap, we explore the scaling limits of GNNs for atomistic materials modeling by developing a foundational model with billions of parameters, trained on extensive datasets in terabytescale. Our approach incorporates techniques from LLM libraries to efficiently manage large-scale data and models, enabling both effective training and deployment of these large-scale GNN models. This work addresses three fundamental questions in scaling GNNs: the potential for scaling GNN model architectures, the effect of dataset size on model accuracy, and the applicability of LLM-inspired techniques to GNN architectures. Specifically, the outcomes of this study include (1) insights into the scaling laws for GNNs, highlighting the relationship between model size, dataset volume, and accuracy, (2) a foundational GNN model optimized for atomistic materials modeling, and (3) a GNN codebase enhanced with advanced LLM-based training techniques. Our findings lay the groundwork for large-scale GNNs with billions of parameters and terabyte-scale datasets, establishing a scalable pathway for future advancements in atomistic materials modeling.

Li, Chaojian [ORNL] (ORCID:0000000340309777)↗

DOE OSTI2025

A knowledge-informed large language model framework for U.S. nuclear power plant shutdown initiating event classification for probabilistic risk assessment

Identifying and classifying shutdown initiating events (SDIEs) is critical for developing shutdown probabilistic risk assessment for nuclear power plants. Existing computational approaches cannot achieve satisfactory performance due to the challenges of unavailable large, labeled datasets, imbalanced event types, and label noise. To address these challenges, we propose a hybrid pipeline that integrates a knowledge-informed machine learning model to prescreen non-SDIEs and a large language model (LLM) to classify SDIEs into four types. In the prescreening stage, we proposed a set of 44 SDIE text patterns that consist of the most salient keywords and phrases from six SDIE types. Text vectorization based on the SDIE patterns generates feature vectors that are highly separable by using a simple binary classifier. The second stage builds Bidirectional Encoder Representations from Transformers (BERT)-based LLM, which learns generic English language representations from self-supervised pretraining on a large dataset and adapts to SDIE classification by fine-tuning it on an SDIE dataset. The proposed approaches are evaluated on a dataset with 10,928 events using precision, recall ratio, F 1 score, and average accuracy. In conclusion, the results demonstrate that the prescreening stage can exclude more than 97% non-SDIEs, and the LLM achieves an average accuracy of 95.1% for SDIE classification.

99 - GENERAL AND MISCELLANEOUS↗

DOE OSTI2025

Leveraging Large Language Models for Real-World Data Evidence: A Framework for Automated Treatment Extraction and Data Harmonization

Background: The ability to comprehensively collect treatment information from cancer patient medical records would enable studies to evaluate real-world benefits and risks tied to specific treatments. Currently, it is difficult to system- atically collect high-quality treatment information because it is often stored in unstructured text. Manually extracting and standardizing drug and regimen data is time-intensive. Recent advances in large language models (LLMs) offer a potential solution for automated extraction of structured treatment information from clinical text. Objective: This study systematically evaluates the utility of four LLMs from the Llama family for automated extraction of oncology treatment information from clinical text. This information can guide researchers using cancer registry data to provide insights into cancer care and outcomes beyond clinical trials. Methods: Four instruction-tuned Llama models with varying parameter counts (1B, 3B, 8B, and 70B) were evaluated for their ability to extract treatment information from clinical documents. A unified oncology knowledge base integrating seven major public data sources was developed to standardize and normalize extracted entities—a critical step for harmonizing data from diverse sources. Extracted treatment data were compared against expert-annotated ground truth. Model performance was assessed using accuracy metrics (Precision, Recall, F1-Score) and opera- tional feasibility metrics, including processing speed and structural compliance of the output. Results: A strong positive correlation was observed between model size and extraction accuracy. F1-score improved from 0.609 for the 1B model to 0.710 (3B), 0.807 (8B), and 0.828 (70B). While larger models demonstrated superior accuracy and compliance, they incurred higher computational costs. The modest performance difference between 8B and 70B suggests diminishing returns with increasing model size. Conclusions: LLMs represent a viable technology for automating oncology treatment extraction. The 8B-parameter model emerged as a highly effective option, balancing high accuracy and computational efficiency. Selecting an appropriate LLM for deployment in cancer registries involves a trade-off between desired accuracy and available operational resources. Harmonizing extracted entities with the oncology knowledge base facilitates standardized integration into common data models, enhancing data quality for real-world evidence analyses.

artificial intelligence↗

DOE OSTI2026

Agentic traffic intelligence: Augmented human-in-the-loop scenario generation for microscopic traffic simulation

Traditional microscopic traffic simulation generation often relies on static datasets and manual design, limiting its ability to simulate complex conditions easily. This paper presents a novel framework, Agentic Traffic Intelligence, which combines human approval large language models (LLMs), the Real-Twin tool, and multi-agent systems to perform realistic microscopic traffic simulation scenario generation. The proposed framework incorporates human-in-the-loop (HIL) control, retrieval-augmented generation (RAG), and multi-agent control mechanisms. HIL mechanisms are used to guide multiple LLMs focused on attributes for microscopic simulation generation and to improve the interpretability and transparency of LLM execution for users. RAG enhances context extraction by dynamically integrating external knowledge sources for traffic scenario generation foundations. A multi-agent architecture with supervisory control coordinates the interaction of simulation components, including traffic simulators, control logic, and calibration tools. This enables the synthesis of simulation-ready scenarios that reflect dynamic demand profiles and behavior controls. Furthermore, the framework fuses multisource traffic data with unstructured context and supports iterative refinement through interactive user feedback. Validated through microscopic simulation using Simulation of Urban Mobility, the generated scenarios demonstrate high-fidelity network generation with inflow and turn movement and behavioral calibration, offering a robust and efficient tool for stress-testing and optimizing urban mobility systems.

Hierarchical multi-agent control↗

DOE OSTI2024

SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions

Instruction finetuning is a popular paradigm to align large language models (LLM) with human intent. Despite its popularity, this idea is less explored in improving the LLMs to align existing foundation models with scientific disciplines, concepts and goals. In this work, we present SciTune as a tuning framework to improve the ability of LLMs to follow scientific multimodal instructions. To test our methodology, we use a human-generated scientific instruction tuning dataset and train a large multimodal model LLaMA-SciTune that connects a vision encoder and LLM for science-focused visual and language understanding. LLaMA-SciTune significantly outperforms the state-of-the-art models in the generated figure types and captions in multiple scientific multimodal benchmarks. In comparison to the models that are fine-tuned with machine generated data only, LLaMA-SciTune surpasses human performance on average and in many sub-categories on the ScienceQA benchmark.

• Artificial intelligence (AI) / machine learning ↗

DOE OSTI2025

Evaluating Economic Impact: An Investment Tool for Large Language Model Integration in Workweek Management

This paper explores the development and application of an investment tool designed to quantify the costs and potential savings associated with integrating large language models (LLMs) into work week management optimization (WMO) within the nuclear industry. LLMs, with their advanced natural language processing capabilities, can significantly enhance various aspects of work management, such as problem identification, prioritization, planning, scheduling, information retrieval, and information summary. Our investment tool focuses on evaluating the return on investment (ROI) for LLM applications in WMO by considering four pivotal decision factors: model selection, application, user training, and hosting options. This paper details the development and implementation of the ROI model and illustrates its application through multiple case studies, analyzing the impact of different variables, such as work time saved, number of requests, and model performance, on the computed ROI over two years. The computed ROI is also compared over different hosting solutions. Our findings indicate that ROI increases with enhanced work time savings and optimal request load but can decline with high request volumes or increased model costs. This model aids decision-makers in the nuclear industry by providing a structured approach to assessing the economic viability and potential savings from integrating LLMs into WMO processes.

97 - MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Evaluating Economic Impact: An Investment Tool for Large Language Model Integration in Workweek Management

99 - GENERAL AND MISCELLANEOUS↗

DOE OSTI2026

ToPolyAgent: AI agents for coarse-grained bead-spring topological polymer simulations

We introduce ToPolyAgent, a multi-agent AI framework for performing coarse-grained molecular dynamics (MD) simulations of topological polymers through natural language instructions. By integrating large language models (LLMs) with domain-specific computational tools, ToPolyAgent supports both interactive and autonomous simulation workflows across diverse polymer architectures, including linear, ring, brush, and star polymers, as well as dendrimers. The system consists of four LLM-powered agents: a Config Agent for generating initial polymer–solvent configurations, a Simulation Agent for executing LAMMPS-based MD simulations and conformational analyses, a Report Agent for compiling markdown reports, and a Workflow Agent for streamlined autonomous operations. Interactive mode incorporates user feedback loops for iterative refinements, while autonomous mode enables end-to-end task execution from detailed prompts. We demonstrate ToPolyAgent's versatility through case studies involving diverse polymer architectures under varying solvent conditions, thermostats, and simulation lengths. Furthermore, we highlight its potential as a research assistant by directing it to investigate the effect of interaction parameters on the linear polymer conformation, and the influence of grafting density on the persistence length of the brush polymer. By coupling natural language interfaces with rigorous simulation tools, ToPolyAgent lowers barriers to complex computational workflows and advances AI-driven materials discovery in polymer science. It lays the foundation for autonomous and extensible multi-agent scientific research ecosystems.

Ding, Lijie [Oak Ridge National Laboratory (ORNL),↗

DOE OSTI2025

Consistent performance of large language models in rare disease diagnosis across ten languages and 4917 cases

Background Large language models (LLMs) are increasingly used medicine for diverse applications including differential diagnostic support. The training data used to create LLMs such as the Generative Pretrained Transformer (GPT) predominantly consist of English-language texts, but LLMs could be used across the globe to support diagnostics if language barriers could be overcome. Initial pilot studies on the utility of LLMs for differential diagnosis in languages other than English have shown promise, but a large-scale assessment on the relative performance of these models in a variety of European and non-European languages on a comprehensive corpus of challenging rare-disease cases is lacking. Methods We created 4917 clinical vignettes using structured data captured with Human Phenotype Ontology (HPO) terms with the Global Alliance for Genomics and Health (GA4GH) Phenopacket Schema. These clinical vignettes span a total of 360 distinct genetic diseases with 2525 associated phenotypic features. We used translations of the Human Phenotype Ontology together with language-specific templates to generate prompts in English, Chinese, Czech, Dutch, French, German, Italian, Japanese, Spanish, and Turkish. We applied GPT-4o, version gpt-4o-2024-08-06, and the medically fine-tuned Meditron3-70B to the task of delivering a ranked differential diagnosis using a zero-shot prompt. An ontology-based approach with the Mondo disease ontology was used to map synonyms and to map disease subtypes to clinical diagnoses in order to automate evaluation of LLM responses. Findings For English, GPT-4o placed the correct diagnosis at the first rank 19.9% and within the top-3 ranks 27.0% of the time. In comparison, for the nine non-English languages tested here the correct diagnosis was placed at rank 1 between 16.9% and 20.6%, within top-3 between 25.4% and 28.6% of cases. The Meditron3 model placed the correct diagnosis within the first 3 ranks for 20.9% of cases in English and between 19.9% and 24.0% for the other nine languages. Interpretation The differential diagnostic performance of LLMs across a comprehensive corpus of rare-disease cases was largely consistent across the ten languages tested. This suggests that the utility of LLMs in clinical settings may extend to non-English clinical settings.

Artificial intelligence↗

DOE OSTI2024

Assessment of fine-tuned large language models for real-world chemistry and material science applications

The current generation of large language models (LLMs) has limited chemical knowledge. Recently, it has been shown that these LLMs can learn and predict chemical properties through fine-tuning. Using natural language to train machine learning models opens doors to a wider chemical audience, as field-specific featurization techniques can be omitted. In this work, we explore the potential and limitations of this approach. We studied the performance of fine-tuning three open-source LLMs (GPT-J-6B, Llama-3.1-8B, and Mistral-7B) for a range of different chemical questions. We benchmark their performances against “traditional” machine learning models and find that, in most cases, the fine-tuning approach is superior for a simple classification problem. Depending on the size of the dataset and the type of questions, we also successfully address more sophisticated problems. The most important conclusions of this work are that, for all datasets considered, their conversion into an LLM fine-tuning training set is straightforward and that fine-tuning with even relatively small datasets leads to predictive models. These results suggest that the systematic use of LLMs to guide experiments and simulations will be a powerful technique in any research study, significantly reducing unnecessary experiments or computations.

Van Herck, Joren↗

DOE OSTI2025

An Open-source Llm Enhanced-tool Specialized In Helping Moose Related Problems And Tasks

MOOSEenger is an open-source, terminal-first chat application for the MOOSE ecosystem that couples specialized parsing of MOOSE documentation and “.i” input files with retrieval-augmented generation to deliver grounded answers about multiphysics modeling and workflows. It includes dedicated readers for MOOSE-style HTML and a pyhit-based parser that uses the MOOSE syntax tree to preserve block structure and attach retrieval metadata. A data-ingestion pipeline performs semantic chunking into atomic facts and stores them hierarchically in a local Chroma vector database that maintains parent–child relationships across documents; the system can ingest directories, individual files, and single-page web content, and it provides CRUD operations (insert, update, delete) to manage the corpus. At query time, relevant chunks are embedded, retrieved, and fused into the model context, with interactive features such as token streaming, persistent chat history, and dynamic RAG (retrieval triggered by user input or intermediate model output). Deployment is flexible: MOOSEenger runs with local Ollama models or remote Hugging Face/OpenAI backends—typically coordinating generation, lightweight tagging/summarization, and embeddings across three models—and it also supports a server mode and integration with the VS Code Continue interface.

Li, Mengnan [Idaho National Laboratory (INL), Idah↗

DOE OSTI2025

Role of Uncertainty Quantification in the Explainability of Large Language Models for the Nuclear Industry

The meteoric rise of generative artificial intelligence (AI) large language models (LLMs) has created an opportunity to utilize them to increase efficiencies in a multitude of industries. While LLMs carry great potential to revolutionize the manner in which work is performed, numerous known deficiencies limit their utility, including the black box nature of the models, the stochastic nature of the response (i.e., presenting the same prompt multiple times results in different responses), and the potential for hallucination. Widespread adoption of LLMs in safety-critical industries such as nuclear will require some form of explainability to assure end users that the LLM’s response to a given query is valid. Model uncertainty is inherently linked to the concepts of trust and explainability, and can be used to identify situations in which the model is insufficiently certain about its answer. Although uncertainty is not enough in and of itself to determine the suitability of an answer—a model can be very certain of an inaccurate answer—it still provides valuable supporting information. Practical methodologies for gauging or quantifying the uncertainty in LLM outputs are presented herein, along with examples based on nuclear-specific prompts.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2026

Dataset of Generative AI Workload Power Profiles

This dataset provides a collection of high-resolution (5/10 Hz or every 0.2/0.1 seconds) power consumption profiles for generative artificial intelligence (GenAI) workloads executed on NLR's High Performance Computing (HPC) platform Kestrel. The dataset also includes examples of representative whole-facility power profiles generated using a bottom-up, event-driven, data center energy model . This dataset is designed to support research in energy modeling, infrastructure planning, energy system integration, and sustainability analysis for AI-driven computing systems. The dataset captures time-resolved electrical power measurements across a diverse set of configurations, including variations in job type (inference vs. training), workload (LLM vs. image generation), datasets, and number of compute nodes. Power traces are provided in a standardized format and include both raw/instantaneous and aggregated files. Each profile is accompanied by metadata describing workload parameters, enabling reproducibility and cross-study comparison. The dataset is intended for use in applications such as data center infrastructure planning, energy modeling, demand response and grid impact studies, and development and validation of system-level simulation tools. By making these workload-specific power profiles publicly available, this dataset aims to address the current lack of open, empirical energy data for generative AI systems and to facilitate transparent, reproducible research on the energy and environmental impacts of large-scale AI deployment. If you use this dataset, please cite the associated publication: Vercellino et al., “Measurement of Generative AI Workload Power Profiles for Whole-Facility Data Center Infrastructure Planning,” arXiv:2604.07345 (2026).

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

El Agente: An autonomous agent for quantum chemistry

Computational chemistry tools are widely used to study the behavior of chemical phenomena. Yet, the complexity of these tools can make them inaccessible to non-specialists and challenging even for experts. In this work, we introduce El Agente Q, an LLM-based multi-agent system that dynamically generates and executes quantum chemistry workflows from natural language user prompts. The system is built on a novel cognitive architecture featuring a hierarchical memory framework that enables flexible task decomposition, adaptive tool selection, post-analysis, and autonomous file handling and submission. El Agente Q is benchmarked on six university-level course exercises and two case studies, demonstrating robust problem-solving performance (averaging >87% task success) and adaptive error handling through in situ debugging. It also supports longer-term, multi-step task execution for more complex workflows, while maintaining transparency through detailed action trace logs. Together, these capabilities lay the foundation for increasingly autonomous and accessible quantum chemistry.

agentic systems↗