SEARCH · Search NASA

Results for “Large Language Model”

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 217 records · Page 12

All sources NASA NTRS DOE OSTI

DOE OSTI2025

AI Benchmark Democratization and Carpentry

Benchmarks are a cornerstone of modern machine learning, enabling reproducibility, comparison, and scientific progress. However, AI benchmarks are increasingly complex, requiring dynamic, AI-focused workflows. Rapid evolution in model architectures, scale, datasets, and deployment contexts makes evaluation a moving target. Large language models often memorize static benchmarks, causing a gap between benchmark results and real-world performance. Beyond traditional static benchmarks, continuous adaptive benchmarking frameworks are needed to align scientific assessment with deployment risks. This calls for skills and education in AI Benchmark Carpentry. From our experience with MLCommons, educational initiatives, and programs like the DOE's Trillion Parameter Consortium, key barriers include high resource demands, limited access to specialized hardware, lack of benchmark design expertise, and uncertainty in relating results to application domains. Current benchmarks often emphasize peak performance on top-tier hardware, offering limited guidance for diverse, real-world scenarios. Benchmarking must become dynamic, incorporating evolving models, updated data, and heterogeneous platforms while maintaining transparency, reproducibility, and interpretability. Democratization requires both technical innovation and systematic education across levels, building sustained expertise in benchmark design and use. Benchmarks should support application-relevant comparisons, enabling informed, context-sensitive decisions. Dynamic, inclusive benchmarking will ensure evaluation keeps pace with AI evolution and supports responsible, reproducible, and accessible AI deployment. Community efforts can provide a foundation for AI Benchmark Carpentry.

von Laszewski, Gregor [Virginia U.]↗

DOE OSTI2025

Review of Grey Box/Black Box Data Contamination Metrics on Open and Commercial Models

Dataset contamination is a problem where benchmarks and tasks used to evaluate the capabilities of Large Language Models (LLMs) have been incorporated into the training dataset of the models. This gives a false sense of performance that can overestimate how these models will function on truly unseen data. This problem becomes worse with commercial LLMs with larger and non-accessible training data, so techniques have been developed to try to measure the degree to which a model is contaminated with a benchmark’s data. To understand the effectiveness of these techniques, particularly when evaluating contamination on coding tasks, we review trends and categorize techniques by the degree of access to the model that is required. The research literature on this topic has reported mixed effectiveness of these techniques, so we select a set of black box (text access only) and grey box (access to model loss/probabilities required) techniques and apply them to both commercial and non-commercial models. We implement these metrics as part of a framework to test the contamination of Python code in LLMs to see to what extent we can replicate the effectiveness (or ineffectiveness) of these contamination detection techniques. Though we find mixed results in the capabilities of these metrics to identify contamination, we do observe evidence that they can identify contamination (broadly) in fine-tuned models when both a baseline and fine-tuned model is present. Additionally, similarity metrics were able to identify between contaminated and uncontaminated data even in situations where the data is distributionally similar (e.g., drawn from the same set of code projects).

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Finch: Toxicity Dose Response Curve Prediction of Chemical Compounds and Mixtures

A paradigm shift in chemical risk assessment is emphasizing mixture testing over single compound analysis, eliminating animal testing, and adopting advanced modeling approaches to understand mixture activity profiles. However, existing computational models largely focus on single chemicals, with few effective solutions for modeling complex mixtures that account for synergistic or antagonistic effects and multiple Modes of Action (MoA). Conventional methods like concentration addition (CA) and independent action (IA) are insufficient for this task as they are designed for simplistic interactions and struggle to account for the dynamic and multifaceted nature of chemical mixtures, such as overlapping MoA and non-linear interactions. Finch offers a novel approach utilizing deep learning (DL) embeddings and multi-task quantitative structure-activity relationship (QSAR) models to improve chemical exposure prediction. By leveraging molecular descriptors, physiochemical properties, and large language model (LLM) embeddings from SMILES inputs, Finch preserves critical information in a latent space thereby enhancing predictive accuracy. The multi-task learning aspect of Finch is highly advantageous, as it simultaneously optimizes multiple loss functions, leveraging all available data across tasks to develop generalized representations that effectively capture complex ingredient interactions within mixtures.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2025

EnergyPlus-MCP: A model-context-protocol server for ai-driven building energy modeling

Traditional building energy modeling with the EnergyPlus building performance simulation engine requires domain expertise, programming skills, and intensive manual efforts limiting its effective adoption. This paper introduces EnergyPlus-MCP, the first open-source Model Context Protocol (MCP) server specifically designed for EnergyPlus simulation workflows, establishing a new foundational infrastructure for AI-driven building energy modeling. The MCP server implements a layered architecture with 35 specialized tools spanning model management, editing and analysis, HVAC and other systems configuration inspection, and simulation execution, enabling Large Language Models to interact with EnergyPlus through conversational interfaces. The server addresses critical workflow barriers by automating model validation, streamlining energy efficiency measures modification, and providing intelligent output management with interactive visualization. Through practical demonstrations using a multi-zone building retrofit analysis, we show how the EnergyPlus-MCP server significantly reduces manual efforts while maintaining full simulation rigor. By providing accessible natural language interfaces to sophisticated building energy analysis, this approach enables scalable deployment of simulation expertise across public and private organizations, educational institutions, and research teams, fundamentally transforming traditional building energy modeling practices.

AI↗

DOE OSTI2025

Intelligent Manufacturing Support: Specialized LLMs for Composite Material Processing and Equipment Operation

Engineering educational curriculum and standards cover many material and manufacturing options. However, engineers and designers are often unfamiliar with certain composite materials or manufacturing techniques. Large language models (LLMs) could potentially bridge the gap. Their capacity to store and retrieve data from large databases provides them with a breadth of knowledge across disciplines. However, their generalized knowledge base can lack targeted, industry-specific knowledge. To this end, we present two LLM-based applications based on the GPT-4 architecture: (1) The Composites Guide: a system that provides expert knowledge on composites material and connects users with research and industry professionals who can provide additional support and (2) The Equipment Assistant: a system that provides guidance for manufacturing tool operation and material characterization. By combining the knowledge of general AI models with industry-specific knowledge, both applications are intended to provide more meaningful information for engineers. In this paper, we discuss the development of the applications and evaluate it through a benchmark and two informal user studies. The benchmark analysis uses the Rouge and Bertscore metrics to evaluate our models’ performance against GPT-4o. The results show that GPT-4o and the proposed models perform similarly or better on the ROUGE and BERTScore metrics. The two user studies supplement this quantitative evaluation by asking experts to provide qualitative and open-ended feedback about our model’s performance on a set of domain-specific questions. The results of both studies highlight a potential for more detailed and specific responses with the Composites Guide and the Equipment Assistant.

Kapoor, Gunnika [Oak Ridge National Laboratory (OR↗

DOE OSTI2025

Enhancing ChatPORT with CUDA-to-SYCL Kernel Translation Capability

Large Language Models (LLMs) have shown strong capabilities in general code translation. However, code translation involving parallel programming models remains largely unexplored. This work enhances the capabilities of code LLMs in CUDA-to-SYCL kernel translation with parameter-efficient fine-tuning. The resultant fine-tuned LLM, called ChatPORT, is an effort to provide high-fidelity translations from one programming model to another. We describe the preparation of datasets from heterogeneous computing benchmarks for model fine-tuning and testing, the parameter-efficient fine-tuning of 19 open-source code models ranging in size from 0.5 to 34 billion parameters and evaluate the correctness rates of the SYCL kernels by the fine-tuned models. The experimental results show that most code models fail to translate CUDA codes to SYCL correctly. However, fine-tuning these models using a small set of CUDA and SYCL kernels can enhance the capabilities of these models in kernel translation. Depending on the sizes of the models, the correctness rate ranges from 19.9% to 81.7% for a test dataset of 62 CUDA kernels.

Jin, Zheming [ORNL] (ORCID:000000027197780X)↗

DOE OSTI2026

Automated Membership Inference Attacks: Discovering MIA Signal Computations using LLM Agents

Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training dataset, have emerged as an important framework to understand, assess, and quantify the potential information leakage associated with machine learning systems. Designing effective MIAs is a challenging task that usually requires extensive manual exploration of model behaviors to identify potential vulnerabilities. In this paper, we introduce AutoMIA -- a novel framework that leverages large language model (LLM) agents to automate the design and implementation of new MIA signal computations. By utilizing LLM agents, we can systematically explore a vast space of potential attack strategies, enabling the discovery of novel strategies. Our experiments demonstrate AutoMIA can successfully discover new MIAs that are specifically tailored to user-configured target model and dataset, resulting in improvements of up to 0.18 in absolute AUC over existing MIAs. This work provides the first demonstration that LLM agents can serve as an effective and scalable paradigm for designing and implementing MIAs with SOTA performance, opening up new avenues for future exploration.

Tran, Toan Viet [Emory University]↗

DOE OSTI2025

Introduction: Neuromorphic Materials

The explosive growth in data collection and the need to process it efficiently, as well as the desire to automate increasingly complex tasks in transportation, medical care, manufacturing, security and many other fields have motivated a growing interest in neuromorphic computing. Unlike the binary, transistorbased ON/OFF logic gates and separate logic and memory functionalities employed in digital computing, neuromorphic computing is inspired by animal brains that use interconnected synapses and neurons to perform processing, storage and transmission of information at the same location, while only consuming ~20 W or less of power. Motivated by the brain’s efficiency, adaptability, self-learning and resiliency qualities, neuromorphic computing can be broadly defined as an approach to processing and storing information using hardware and algorithms inspired by models of biological neural systems. Present research in neuromorphic computing encompasses approaches that vary significantly in their degree of neuro-inspiration, from systems that only incorporate features such as asynchronous, event-driven operation or use crossbar arrays of non-volatile memory (NVM) elements to accelerate deep neural networks (DNNs), to designs that embrace the extreme parallelism, sparsity, reconfigurability, adaptability, complexity and stochasticity observed in nervous systems. The term ‘neuromorphic’ computing is often credited to Carver Mead, who in the 1980s investigated Si-based analog electronics to replicate functions of the animal retina. Earlier important advances in this field include the work of Frank Rosenblatt, who proposed the concept of the perceptron, Bernard Widrow, who used this concept to build one of the first analog neural networks, the Adaline and many other researchers (see ref. 6 for an historical perspective on neuromorphic computing). With the recent increase in the use of artificial intelligence and large language models, and rising concerns over the associated energy costs, interest in neuromorphic hardware has expanded rapidly. According to some estimates, driven largely by the drastic growth in the training use of artificial intelligence (AI) models using the current computing architectures, the energy cost of computing is projected to reach the energy supply worldwide by 2045. Furthermore, while this is not a realistic outcome, it means that, if more efficient computing technologies are not developed -- soon -- the world will soon become one where demand for energy and market constraints limit the continued increase of societal access to AI and cloud services from data centers. Data centers used for training and use of these models consume hundreds of terawatt hours of electricity, already past 4% of the US electricity demand.

Circuits↗

DOE OSTI2024

GraphAide: Advanced Graph-Assisted Query and Reasoning System

Curating knowledge from multiple siloed sources that contain both structured and unstructured data is a major challenge in many real-world applications. Pattern matching and querying represent fundamental tasks in modern data analytics that leverage this curated knowledge. The development of such applications necessitates overcoming several research challenges, including data extraction, named entity recognition, data modeling, and designing query interfaces. Moreover, the explainability of these functionalities is critical for their broader adoption. The emergence of Large Language Models (LLMs) has accelerated the development lifecycle of new capabilities. Nonetheless, there is an ongoing need for domain-specific tools tailored to user activities. The creation of digital assistants has gained considerable traction in recent years, with LLMs offering a promising avenue to develop such assistants utilizing domain-specific knowledge and assumptions. In this context, we introduce an advanced query and reasoning system, GraphAide, which constructs a knowledge graph (KG) from diverse sources and allows to query and reason over the resulting KG. GraphAide harnesses both the KG and LLMs to rapidly develop domain-specific digital assistants. It integrates design patterns from retrieval augmented generation (RAG) and the semantic web to create an agentic LLM application. GraphAide underscores the potential for streamlined and efficient development of specialized digital assistants, thereby enhancing their applicability across various domains.

Purohit, Sumit [BATTELLE (PACIFIC NW LAB)] (ORCID:↗

DOE OSTI2026

Design and performance of AI agents interfacing with an atomic layer deposition tool

In this work, we introduce the design of an atomic layer deposition (ALD) reactor augmented with an AI interface for autonomous materials synthesis. Our modular design encapsulates the particularities of the hardware behind a Python interface that communicates with the ALD control software via transmission control protocol. This interface is compatible with model context protocol interfaces used in agentic frameworks. We have integrated our tool with a simple AI agent that leverages a large language model to transform user-supplied queries into ALD processes that are then run in our reactor. Our approach uses a JavaScript object notation schema to encode ALD processes. Our experimental results show that the AI interface does not impose a significant overhead to our control software, at least within our fastest 10 ms scale. We also carried out a detailed evaluation of the agent performance using leading models in two classes of tasks: basic instruction and process discovery tasks, where the agent is presented with a target material and needs to identify the correct ALD process compatible with the reactor configuration. Despite the simplicity of our agent design, we observed that most of the advanced models excelled at the instruction tasks. However, only recent models, such as o1, o3, GPT-5, and Claude Opus 4, performed well in process discovery tasks. We also observed significant variability in the response for the hardest challenges. While the results obtained are promising, we identify areas where AI research could improve the performance of agents for ALD.

47 OTHER INSTRUMENTATION↗

DOE OSTI2025

Scientific Open-Source Software Is Less Likely to Become Abandoned Than One Might Think! Lessons from Curating a Catalog of Maintained Scientific Software

Scientific software is essential to scientific innovation and in many ways it is distinct from other types of software. Abandoned (or unmaintained), buggy, and hard to use software, a perception often associated with scientific software can hinder scientific progress, yet, in contrast to other types of software, its longevity is poorly understood. Existing data curation efforts are fragmented by science domain and/or are small in scale and lack key attributes. We use large language models to classify public software repositories in World of Code into distinct scientific domains and layers of the software stack, curating a large and diverse collection of over 18,000 scientific software projects. Using this data, we estimate survival models to understand how the domain, infrastructural layer, and other attributes of scientific software affect its longevity. We further obtain a matched sample of non-scientific software repositories and investigate the differences. We find that infrastructural layers, downstream dependencies, mentions of publications, and participants from government are associated with a longer lifespan, while newer projects with participants from academia had shorter lifespan. Against common expectations, scientific projects have a longer lifetime than matched non-scientific open-source software projects. We expect our curated attribute-rich collection to support future research on scientific software and provide insights that may help extend longevity of both scientific and other projects.

Malviya Thakur, Addi [ORNL] (ORCID:000000022681999↗

NASA NTRSDate not supplied

A Case Study of AI-assisted Creation of a Thermodynamics Model of Precipitation Formation During Rapid Depressurization of a Vented Container

Precipitation may form in humid containers undergoing rapid depressurization. This precipitation may be liquid, i.e. fog, if the dewpoint is crossed above the freezing point of water, or direct snow crystallization if the dewpoint is crossed below the freezing point. Accurate modeling of this effect is potentially important for rapidly ascending vented containers in aircraft, spacecraft, and launch vehicles, as well as rapidly depressurizing vacuum chambers. A transient thermodynamics model of precipitation formation during the rapid depressurization of a container was developed in python. The model is written for a generic container and includes an optional water pool and water vapor source. Details of the model and results from several example cases spanning the full capabilities of the model, including a validation case, will be presented. Although the model is not novel, in contrast to prior works, this one was treated as a case study of the assistance of AI Large Language Models (LLMs) to create physical models. Impressions, performance, time, and cost of using AI for this task will be discussed.

precipitation↗

DOE OSTI2026

Coupling Noah-Multiparameterization land-surface Model with Energy Research and Forecasting Model

The Energy Research and Forecasting (ERF) model is a high-performance atmospheric model built on the AMReX adaptive mesh refinement (AMR) framework, enabling efficient simulations on heterogeneous computing platforms that combine multicore processors with hardware accelerators. To support land–atmosphere interactions within ERF’s AMR-based environment, a land-surface model must be capable of operating directly on hierarchically refined meshes. In this work, we present a methodology for coupling the Fortran-based Noah-Multiparameterization (Noah-MP) land-surface model with ERF’s C++ codebase. Rather than rewriting Noah-MP, we construct a Fortran–C interoperability layer using CodeScribe, a tool that leverages large language models (LLMs) to automate the generation of interface code. CodeScribe applies structured prompting techniques to generate bindings that support efficient data exchange and function calls between ERF and Noah-MP. The coupling framework also incorporates AMR-aware data handling strategies, allowing NoahMP to operate seamlessly within ERF’s hierarchical mesh structure. This work provides a structured approach for integrating legacy Fortran models into modern C++-based modeling systems using LLM-assisted code generation.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2026

XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts

Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages into Large Language Model (LLM)-generated text, enabling reliable attribution and tracing of malicious usage of LLMs. Despite recent progress, existing methods still face key limitations: some become computationally infeasible for large messages, while others suffer from a poor trade-off between text quality and decoding accuracy. Moreover, the decoding accuracy of existing methods drops significantly when the number of tokens in the generated text is limited, a condition that frequently arises in practical usage. To address these challenges, we propose XMark, a novel method for encoding and decoding binary messages in LLM-generated texts. The unique design of XMark’s encoder produces a less distorted logit distribution for watermarked token generation, preserving text quality, and also enables its tailored decoder to reliably recover the encoded message with limited tokens. Extensive experiments across diverse downstream tasks show that XMark significantly improves decoding accuracy while preserving the quality of watermarked text, outperforming prior methods. The code will be made publicly available upon acceptance.

Xu, Jiahao [University of Nevada, Reno]↗

DOE OSTI2026

Deep learning for time series forecasting: a survey of recent advances

Time series forecasting plays a critical role in numerous real-world applications, such as finance, healthcare, transportation, and scientific computing. In recent years, deep learning has become a powerful tool for modeling complex temporal patterns and improving forecasting accuracy. This survey provides an overview of recent deep learning approaches for time series forecasting, involving various architectures including RNNs, CNNs, GNNs, transformers, large language models, MLP-based models, and diffusion models. We first identify key challenges in the field, such as temporal dependency, efficiency, and cross-variable dependency, which drive the development of forecasting techniques. Then, the general advantages and limitations of each architecture are discussed to contextualize their adaptation in time series forecasting. Furthermore, we highlight promising design trends like multi-scale modeling, decomposition, and frequency-domain techniques, which are shaping the future of the field. This paper serves as a compact reference for researchers and practitioners seeking to understand the current landscape and future trajectory of deep learning in time series forecasting.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Site-decorated model for unconventional frustrated magnets: Ultranarrow phase crossover and two-dimensional spin reversal transition

Here, the site-decorated Ising model is introduced to advance the understanding and experimental realization of the recently discovered one-dimensional (1D) finite-temperature ultranarrow phase crossover in an external magnetic field, while mitigating the geometric complexities of traditional bond-decorated models. The unconventional frustration and physics are clarified by exactly mapping the 1D site-decorated Ising model in a magnetic field onto a zero-field bond-decorated 𝐽 1 −𝐽 2 Ising model with conventional geometrical frustration. Furthermore, although higher-dimensional Ising models in an external field remain unsolved exactly, an exact solution for a spin-reversal transition—driven by an exotic, hidden half-ice, half-fire state induced by site decoration—is derived. This transition, triggered by a slight variation in temperature or magnetic field—without changing its direction—even in the weak-field limit, offers a promising route toward energy-efficient applications such as data storage and processing. The results suggest that site decoration offers an avenue for materials and device design, particularly in systems such as mixed 𝑑−𝑓 compounds, optical lattices, and neural networks, calling for further studies with site-decorated Heisenberg models. In addition, the site-decorated model offers a rigorous test ground for artificial intelligence (AI) in science, as the analytic derivation of the present results was not only validated but also improved by a general-purpose large language model, inspiring the use of AI as scientific discoverer.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2025

Coreii - Scout

COREII Scout employs React, Vite, TypeScript, Tailwind, and Daisy UI for its graphical user interface (GUI), offering both dark and light modes. The code is modular, with components and reusable wrappers to enhance efficiency. The primary goal of COREII Scout is to aid analysts in collecting and analyzing various sources related to cyber attacks, utilizing models to automate the report writing process. It uses Named Entity Recognition (NER), a type of Natural Language Processing (NLP), to extract key entities from each source. Analysts review and classify these entities using the COREII Attack Chain Estimator (ACE), adding their comments. Ultimately, a Large Language Model (LLM) generates a detailed report with user guidance. This setup ensures a streamlined and effective approach to cyber attack analysis and reporting.

Pluth, Adam [Idaho National Laboratory (INL), Idah↗

DOE OSTI2026

BrickQA: Bridging the Semantic Gap in Building Operations with Dynamic Graph Exploration

While standardized ontologies like the Brick schema address data heterogeneity in Building Automation Systems (BAS), accessing this semantic data remains a challenge as domain experts often lack the expertise to formulate complex SPARQL queries. To bridge this gap, we present BrickQA, a Large Language Model (LLM)-based framework that translates natural language into executable SPARQL queries through structured query decomposition, dynamic schema exploration, and inline validation. BrickQA utilizes an iterative reasoning agent to actively navigate graph topology through dynamic exploration actions without requiring exhaustive context injection or model fine-tuning. This approach effectively mitigates hallucinations, particularly in large-scale building knowledge graphs. Empirical evaluation on BuildingQA, a standardized benchmark, demonstrates that BrickQA significantly outperforms ReAct baselines, delivering a 0.291–0.355 absolute F1 improvement while achieving 3 × –12.7 × higher token cost-efficiency. Beyond these metrics, the framework maintains structural fidelity across heterogeneous buildings and remains resilient to ambiguous queries without requiring site-specific fine-tuning. Furthermore, a case study on operational analytics validates the framework’s capability to handle temporal and aggregation constraints, effectively transforming abstract semantic models into actionable facility management insights.1

Ko, Yun-Dam↗