Search NASA⌕ Search

SEARCH · Search NASA

Results for “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.

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

At least 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Enhancing Dataset Discovery and Usage Tracking in Earth Sciences: Integrating Knowledge Graphs and Large Language Models

NASA's Data Active Archive Centers (DAACs) have played a crucial role in supporting a wide range of applied research in Earth and Environmental sciences. To date, over 20,000 publications have been collected, citing more than 3,000 NASA Earth science datasets. We present an innovative approach that links datasets and collected publications through a knowledge graph (KG). This KG enables the tracking of dataset citations throughout the dataset's lifecycle, revealing patterns of dataset usage across various applied research areas. We fine-tuned the pre-trained NASA IMPACT INDUS-Base Retriever Large Language Model (LLM) using a set of labeled publication abstracts. Our results indicate that 87% of the publications were classified into one of twenty applied research areas, while the remaining 13% were categorized into non-applied research areas. The classified publications linked to datasets are used to discover datasets by users interested in specific applied research and by dataset providers to determine dataset usage for applications.

open-source↗
DOE OSTI2024

Semantic Stealth: Crafting Covert Adversarial Patches for Sentiment Classifiers Using Large Language Models

Deep learning models have been shown to be vulnerable to adversarial attacks, in which perturbations to their inputs cause the model to produce incorrect predictions. As opposed to adversarial attacks in computer vision, where small changes introduced to pixel values can drastically alter a model's output while remaining imperceptible to humans, text-based attacks are difficult to conceal due to the discrete nature of tokens. Consequently, unconstrained gradient-based attacks often produce adversarial examples that lack semantic meaning, rendering them detectable through visual inspection or perplexity filters. In contrast to methods that rely on gradient-based optimization in the embedding space, we propose an approach that leverages a Large Language Model's ability to generate grammatically correct and semantically meaningful text to craft adversarial patches that seamlessly blend in with the original input text. These patches can be used to alter the behavior of a target model, such as a text classifier. Since our approach does not rely on gradient backpropagation, it only requires access to the target model's confidence scores, making it a grey-box attack. We demonstrate the feasibility of our approach using open-source LLMs, including Intel's Neural Chat, Llama2, and Mistral-Instruct, to generate adversarial patches capable of altering the predictions of a distilBERT model fine-tuned on the IMDB reviews dataset for sentiment classification.

Roa Carvajal, Maria↗
DOE OSTI2025

Causal discovery from data assisted by large language models

Knowledge-driven discovery of novel materials necessitates the development of causal models for property emergence. While in the classical physical paradigm, the causal relationships are deduced based on physical principles or via experiment, the rapid accumulation of observational data necessitates learning causal relationships between dissimilar aspects of material structure and functionalities based on observations. For this, it is essential to integrate experimental data with prior domain knowledge. Here, we demonstrate this approach by combining high-resolution scanning transmission electron microscopy data with insights derived from large language models (LLMs). By applying ChatGPT to domain-specific literature, such as arXiv papers on ferroelectrics, and combining the obtained information with data-driven causal discovery, we construct adjacency matrices for directed acyclic graphs that map the causal relationships between structural, chemical, and polarization degrees of freedom in Sm-doped BiFeO 3 . This approach enables us to hypothesize how synthesis conditions influence material properties and guides experimental validation. Furthermore, the ultimate objective of this work is to develop a unified framework that integrates LLM-driven literature analysis with data-driven discovery, facilitating the precise engineering of ferroelectric materials by establishing clear connections between synthesis conditions and their resulting material properties.

Causal inference↗
DOE OSTI2025

Using a Large Language Model as a Building Block to Generate Usable Validation and Verification Suite for OpenMP

In the HPC area, both hardware and software move quickly. Often new hardware is developed and deployed, the corresponding software stack, including compilers and other tools, are under active development while leading edge software developers are working to port and tune their applications, all at the same time. While the software ecosystem is in flux, one of the key challenges for users is obtaining insight into the state of implementation of key features in the programming languages and models their applications are using – whether they have been implemented, and whether the implementation conforms to the specification, especially for newly implemented features (less tested by widespread use). OpenMP is one of the most prominent shared memory programming models used for on-node programming in HPC. With the shift towards accelerators (such as GPUs and FPGAs) and heterogeneous programming OpenMP features are getting more complex. It is natural to ask whether generative AI approaches, and large language models (LLMs) in particular, can help in producing validation and verification test suites to allow users better and faster insights into the availability and correctness of OpenMP features of interest. In this work, we explore the use of ChatGPT-4 to generate a suite of tests for OpenMP features. We have chosen a set of directives and clauses, a total of 78 combinations, which first appeared in OpenMP 3.0 (released in May 2008) but are also relevant for accelerators. We prompted ChatGPT to generate tests in the C and Fortran languages, for both host (CPU) and device (accelerator). On the Summit super-computer using the GNU implementation, we found that, of the 78 generated tests 67 C tests and 43 Fortran tests compiled successfully and fewer than those executed to completion. On further analysis we show that not all generated tests are valid. We document the process, results, and provide detailed analysis regarding the quality of tests generated. With the aim of providing input to a production quality validation and verification suite, we manually implement the corrections required to make the tests valid according to the current OpenMP specification. We quantify this effort as small, medium, or large, and record the lines of code changed to correct the invalid tests. With the corrected tests we validate recent implementations from HPE, AMD, and GNU on the Frontier supercomputer. Our experiment and subsequent analysis show that although LLMs are capable of producing HPC specific codes, they are limited by their understanding of the deeper semantics and restrictions of programming models such as OpenMP. Unsurprisingly more commonly used features have better support, while some OpenMP 3.0 directives such as sections and tasking are not universally supported on accelerators. We demonstrate that successful compilation and execution to completion are inadequate metrics for evaluating generated code and that, at this time, commodity LLMs require expert intervention for code verification. This points to gaps in the training data that is currently available for HPC. We demonstrate that with "small" effort 37% of generated invalid C tests and 63% of generated invalid Fortran tests could be corrected. This improves productivity of test generation as we circumvent writing from scratch and the common programming errors associated with it.

Pophale, Swaroop [ORNL] (ORCID:0000000185446367)↗
DOE OSTI2025

Computational toolkit for predicting thickness of 2D materials using machine learning and autogenerated dataset by large language model

The thickness of 2D materials not only plays a crucial role in determining the performance of nanoelectronic and optoelectronic devices but also introduces complexities in predicting volume-dependent properties, such as energy storage capacity, due to the intrinsic vacuum within these materials. Although a plethora of experimental techniques, including but not limited to optical contrast, Raman spectroscopy, nonlinear optical spectroscopy, near-field optical imaging, and hyperspectral imaging, facilitate the measurement of 2D material thickness, comprehensive data for many materials remain elusive. Over the past decade, the exponential proliferation of 2D materials and their heterostructures has outstripped the capabilities of conventional experimental and computational approaches. In this evolving landscape, machine learning (ML) has emerged as an indispensable tool, offering a scalable approach to augment these traditional methodologies. Addressing the critical gap, we introduce THICK2D—Thickness Hierarchy Inference and Calculation Kit for 2D Materials. This Python-based computational framework harnesses an autogenerated thickness database, developed using large language models, and advanced ML algorithms to facilitate the rapid and scalable estimation of material thickness, relying solely on crystallographic data. To demonstrate the utility and robustness of THICK2D, we successfully used the toolkit to predict the thickness of more than 8000 2D-based materials, sourced from two extensive 2D materials databases. THICK2D is disseminated as an open-source utility, accessible on GitHub at https://github.com/gmp007/THICK2D, and archived on Zenodo at https://10.5281/zenodo.11216648.

Ekuma, Chinedu E. (ORCID:0000000258527556)↗
NASA NTRSDate not supplied

Discovering Research Areas in Dataset Applications Through Knowledge Graphs and Large Language Models

Scientific datasets are increasingly cited in peer-reviewed journal publications, facilitating easy access to research utilizing those datasets. Datasets undergo a life cycle where older versions of datasets are replaced by newer versions often due to improvements in data resolution, algorithms, and other factors. Unlike peer reviewed documents registered with a single Digital Unique Identifier (DOI), datasets can be updated over time and the newer version of the datasets are registered with a new DOI which is not necessarily linked to the previous version of the dataset. It is challenging when publications citing a dataset need to be traced over the entire life cycle of that dataset. We provide an innovative approach to link the dataset versions and publications using a knowledge graph (KG). KG can help to trace the dataset cited in publications over the entire dataset life cycle and shed light into dataset usage in various applied research areas. We fine-tuned the pretrained NASA IMPACTINDUS Large Language Model (LLM) on a set of labeled publications abstracts. Our results showed that 87% of the publications were classified into one of twenty applied research areas, while the remaining 13% were classified into non-applied research areas. By linking datasets to applied research areas through the KG and employing Global Change Master Directory(GCMD), a well-established controlled vocabulary of scientific keywords describing Earth science datasets, we contribute to a transparent and advanced search and discovery mechanism for datasets across the Earth data ecosystem. The integrated KG and LLM approach is now incorporated and operational in dataset publication management at one of NASA’s Earth science data archival centers.

data provenance↗
NASA NTRSDate not supplied

Concept-based Analysis of Neural Networks via Vision-Language Models

The analysis of vision-based deep neural networks (DNNs) is highly desirable but it is very challenging due to the difficulty of expressing formal specifications for vision tasks and the lack of efficient verification procedures. In this paper, we propose to leverage emerging multimodal, vision-language, foundation models (VLMs) as a lens through which we can reason about vision models. VLMs have been trained on a large body of images accompanied by their textual description, and are thus implicitly aware of high-level, human-understandable concepts describing the images. We describe a logical specification language Con spec designed to facilitate writing specifications in terms of these concepts. To define and formally check Con spec specifications, we build a map between the internal representations of a given vision model and a VLM, leading to an efficient verification procedure of natural-language properties for vision models. We demonstrate our techniques on a ResNet-based classifier trained on the RIVAL-10 dataset using CLIP as the multimodal model.

Large Vision Language Models↗
NASA NTRS2018

Definition of Modeling vs. Programming Languages

Modeling languages (like UML and SysML) are those used in modelbased specification of software-intensive systems. Like programming languages, they are defined using their syntax and semantics. However, both kinds of languages are defined by different communities, and in response to different requirements, which makes their methodologies and tools different. In this paper, we highlight the main differences between the definition methodologies of modeling and programming languages. We also discuss the impact of these differences on language tool support. We illustrate our ideas using examples from known programming and modeling languages. We also present a case study, where we analyze the definition of a new modeling language called the Ontology Modeling Language (OML). We highlight the requirements that have driven OML definition and explain how they are different from those driving typical programming languages. Finally, we discuss how these differences are being abstracted away using new language definition tools.

Elaasar, Maged↗
DOE OSTI2025

Achieving GPT-4o level performance in astronomy with a specialized 8B-parameter large language model

AstroSage-Llama-3.1-8B is a domain-specialized natural-language AI assistant tailored for research in astronomy, astrophysics, cosmology, and astronomical instrumentation. Trained on the complete collection of astronomy-related arXiv papers from 2007 to 2024 along with millions of synthetically-generated question-answer pairs and other astronomical literature, AstroSage-Llama-3.1-8B demonstrates remarkable proficiency on a wide range of questions. AstroSage-Llama-3.1-8B scores 80.9% on the AstroMLab-1 benchmark, greatly outperforming all models—proprietary and open-weight—in the 8-billion parameter class, and performing on par with GPT-4o. This achievement demonstrates the potential of domain specialization in AI, suggesting that focused training can yield capabilities exceeding those of much larger, general-purpose models. AstroSage-Llama-3.1-8B is freely available, enabling widespread access to advanced AI capabilities for astronomical education and research.

AI assistant↗
DOE OSTI2024

Designing complex concentrated alloys with quantum machine learning and language modeling

Designing novel complex concentrated alloys (CCAs) is an essential topic in materials science. However, due to the complicated high-dimensional component-property relationship, tuning material properties by researchers’ experience is challenging, even when guided by physical or empirical rules. Here, we adopt quantum computing (QC) technology and machine learning models to provide a proof-of-concept application of QC in physical metallurgy. We propose a quantum support vector machine (QSVM) model to predict single-phase CCAs. We show that fine-tuned quantum kernels with entanglement deliver promising performance, with a maximum accuracy of 89.4%. The QSVM model is then used to identify 1,741 lightweight CCAs jointly with a new text-mining-based method. Meanwhile, we devise a controllable approach to study the effect of noise on model performance and find that the noise level needs to be minimized for high-performance QSVM models. Finally, this study provides a practical and general approach to designing CCAs based on quantum technologies.

36 MATERIALS SCIENCE↗
DOE OSTI2026

System-Level Integration of Modular Language Models for Real-Time Risk Assessment in Third-Party Risk Management Systems

Large enterprises typically rely on dedicated teams to govern and implement security measures throughout their supply chains, ensuring compliance with enterprise security procedures. There is a significant reliance on Third-Party Risk Management (TPRM) platforms, which often require complete, highly structured information from potential vendors. The review and compliance assurance processes are time- and labor intensive, often requiring several rounds of review between the supply chain security risk management teams, business users, and potential vendors, leading to delays in the supply chain processing and consumer experience. Significant challenges in the risk management paradigm include handling unstructured data in various formats and providing real-time feedback to users to reduce the required review time. This paper presents a novel solution to these challenges. A modular multi-step system architecture is proposed using advances in language processing, specifically for unstructured responses and provides real-time feedback (i.e., 3 seconds) so that users can improve their responses before the TPSRM team review. This novel system architecture will increase information accuracy and significantly reduce time and labor during the review process.

99 - GENERAL AND MISCELLANEOUS↗
NASA NTRSDate not supplied

Identifying Human Errors and Error Mechanisms From Accident Reports Using Large Language Models

Emerging operational concepts for aviation hinge on novel paradigms for human machine interaction. Critical to their safe operation is early consideration of human error into the design process. Existing methods for consideration of human error require significant expert input, which is challenging both in early design and in novel systems for which there is little existing safety expertise. In this research, we propose a methodology for identifying human error, error producing factors, and mechanisms in early design from historical incident reports. Additionally, we hypothesize that cross-domain sharing of lessons learned can aid with early design human considerations in circumstances where data is not relevant or incomplete. This is addressed by identifying causes of human error in aviation and railway domains through applying state-of-the art natural language processing techniques to historical incident reports. Using this method, it is possible to extract extensive reports on human error from past incidents. Using the proposed approach, we identify nine human errors from railway reports and fourteen from aviation reports, with three errors common to both domains. There is at least one error producing conditions for each human error while a majority of the errors have more than one error mechanism. We also found that a majority of the human errors, error producing factors, and error mechanisms (even if they are not common between the domains) can be used to inform safe operations across domains as long as the errors are not domain specific and are interpreted and contextualized using engineering judgement.

Human Errors↗